Tao Shen


pdf bib
CCPrefix: Counterfactual Contrastive Prefix-Tuning for Many-Class Classification
Yang Li | Canran Xu | Guodong Long | Tao Shen | Chongyang Tao | Jing Jiang
Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)

Recently, prefix-tuning was proposed to efficiently adapt pre-trained language models to a broad spectrum of natural language classification tasks. It leverages soft prefix as task-specific indicators and language verbalizers as categorical-label mentions to narrow the formulation gap from pre-training language models. However, when the label space increases considerably (i.e., many-class classification), such a tuning technique suffers from a verbalizer ambiguity problem since the many-class labels are represented by semantic-similar verbalizers in short language phrases. To overcome this, inspired by the human-decision process that the most ambiguous classes would be mulled over for an instance, we propose a brand-new prefix-tuning method, Counterfactual Contrastive Prefix-tuning (CCPrefix), for many-class classification. Basically, an instance-dependent soft prefix, derived from fact-counterfactual pairs in the label space, is leveraged to complement the language verbalizers in many-class classification. We conduct experiments on many-class benchmark datasets in both the fully supervised setting and the few-shot setting, which indicates that our model outperforms former baselines.

pdf bib
Corpus-Steered Query Expansion with Large Language Models
Yibin Lei | Yu Cao | Tianyi Zhou | Tao Shen | Andrew Yates
Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)

Recent studies demonstrate that query expansions generated by large language models (LLMs) can considerably enhance information retrieval systems by generating hypothetical documents that answer the queries as expansions. However, challenges arise from misalignments between the expansions and the retrieval corpus, resulting in issues like hallucinations and outdated information due to the limited intrinsic knowledge of LLMs. Inspired by Pseudo Relevance Feedback (PRF), we introduce Corpus-Steered Query Expansion (CSQE) to promote the incorporation of knowledge embedded within the corpus. CSQE utilizes the relevance assessing capability of LLMs to systematically identify pivotal sentences in the initially-retrieved documents. These corpus-originated texts are subsequently used to expand the query together with LLM-knowledge empowered expansions, improving the relevance prediction between the query and the target documents. Extensive experiments reveal that CSQE exhibits strong performance without necessitating any training, especially with queries for which LLMs lack knowledge.


pdf bib
Towards Robust Ranker for Text Retrieval
Yucheng Zhou | Tao Shen | Xiubo Geng | Chongyang Tao | Can Xu | Guodong Long | Binxing Jiao | Daxin Jiang
Findings of the Association for Computational Linguistics: ACL 2023

A neural ranker plays an indispensable role in the de facto ‘retrieval & rerank’ pipeline, but its training still lags behind due to the weak negative mining during contrastive learning. Compared to retrievers boosted by self-adversarial (i.e., in-distribution) negative mining, the ranker’s heavy structure suffers from query-document combinatorial explosions, so it can only resort to the negative sampled by the fast yet out-of-distribution retriever. Thereby, the moderate negatives compose ineffective contrastive learning samples, becoming the main barrier to learning a robust ranker. To alleviate this, we propose a multi-adversarial training strategy that leverages multiple retrievers as generators to challenge a ranker, where i) diverse hard negatives from a joint distribution are prone to fool the ranker for more effective adversarial learning and ii) involving extensive out-of-distribution label noises renders the ranker against each noise distribution, leading to more challenging and robust contrastive learning. To evaluate our robust ranker (dubbed R2anker), we conduct experiments in various settings on the passage retrieval benchmarks, including BM25-reranking, full-ranking, retriever distillation, etc. The empirical results verify the new state-of-the-art effectiveness of our model.

pdf bib
Length-Adaptive Distillation: Customizing Small Language Model for Dynamic Token Pruning
Chang Liu | Chongyang Tao | Jianxin Liang | Jiazhan Feng | Tao Shen | Quzhe Huang | Dongyan Zhao
Findings of the Association for Computational Linguistics: EMNLP 2023

Pre-trained language models greatly improve the performance of various tasks but at a cost of high computation overhead. To facilitate practical applications, there are mainly two lines of research to accelerate model inference: model compression and dynamic computation (e.g., dynamic token pruning). Existing works either adopt these methods individually or simply apply dynamic computation approaches upon a compressed small language model. We argue that they are sub-optimal since the two approaches are separately designed so the compressed model may not be tailored for dynamic computation. To tackle this problem and make compressed small language models faster, we propose Length-Adaptive Distillation, a two-stage knowledge distillation framework that aims to produce a customized small language model for dynamic token pruning. In the general distillation stage, we enforce the student to mimic and reconstruct the teacher’s output based on the dynamically pruned representations. Then in the task-specific distillation stage, the student is further accustomed to token pruning while absorbing the task-specific knowledge. Experimental results on GLUE benchmark demonstrate that our method can make the small language model more customized for dynamic token pruning and achieve better speed-performance trade-off.

pdf bib
FAA: Fine-grained Attention Alignment for Cascade Document Ranking
Zhen Li | Chongyang Tao | Jiazhan Feng | Tao Shen | Dongyan Zhao | Xiubo Geng | Daxin Jiang
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Document ranking aims at sorting a collection of documents with their relevance to a query. Contemporary methods explore more efficient transformers or divide long documents into passages to handle the long input. However, intensive query-irrelevant content may lead to harmful distraction and high query latency. Some recent works further propose cascade document ranking models that extract relevant passages with an efficient selector before ranking, however, their selection and ranking modules are almost independently optimized and deployed, leading to selecting error reinforcement and sub-optimal performance. In fact, the document ranker can provide fine-grained supervision to make the selector more generalizable and compatible, and the selector built upon a different structure can offer a distinct perspective to assist in document ranking. Inspired by this, we propose a fine-grained attention alignment approach to jointly optimize a cascade document ranking model. Specifically, we utilize the attention activations over the passages from the ranker as fine-grained attention feedback to optimize the selector. Meanwhile, we fuse the relevance scores from the passage selector into the ranker to assist in calculating the cooperative matching representation. Experiments on MS MARCO and TREC DL demonstrate the effectiveness of our method.

pdf bib
CORE: Cooperative Training of Retriever-Reranker for Effective Dialogue Response Selection
Chongyang Tao | Jiazhan Feng | Tao Shen | Chang Liu | Juntao Li | Xiubo Geng | Daxin Jiang
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Establishing retrieval-based dialogue systems that can select appropriate responses from the pre-built index has gained increasing attention. Recent common practice is to construct a two-stage pipeline with a fast retriever (e.g., bi-encoder) for first-stage recall followed by a smart response reranker (e.g., cross-encoder) for precise ranking. However, existing studies either optimize the retriever and reranker in independent ways, or distill the knowledge from a pre-trained reranker into the retriever in an asynchronous way, leading to sub-optimal performance of both modules. Thus, an open question remains about how to train them for a better combination of the best of both worlds. To this end, we present a cooperative training of the response retriever and the reranker whose parameters are dynamically optimized by the ground-truth labels as well as list-wise supervision signals from each other. As a result, the two modules can learn from each other and evolve together throughout the training. Experimental results on two benchmarks demonstrate the superiority of our method.

pdf bib
UniEvent: Unified Generative Model with Multi-Dimensional Prefix for Zero-Shot Event-Relational Reasoning
Zhengwei Tao | Zhi Jin | Haiyan Zhao | Chengfeng Dou | Yongqiang Zhao | Tao Shen | Chongyang Tao
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Reasoning about events and their relations attracts surging research efforts since it is regarded as an indispensable ability to fulfill various event-centric or common-sense reasoning tasks. However, these tasks often suffer from limited data availability due to the labor-intensive nature of their annotations. Consequently, recent studies have explored knowledge transfer approaches within a multi-task learning framework to address this challenge. Although such methods have achieved acceptable results, such brute-force solutions struggle to effectively transfer event-relational knowledge due to the vast array of inter-event relations (e.g. temporal, causal, conditional) and reasoning formulations (e.g. discriminative, abductive, ending prediction). To enhance knowledge transfer and enable zero-shot generalization among various combinations, in this work we propose a novel unified framework, called UNIEVENT. Inspired by prefix-based multitask learning, our approach organizes event relational reasoning tasks into a coordinate system with multiple axes, representing inter-event relations and reasoning formulations. We then train a unified text-to-text generative model that utilizes coordinate-assigning prefixes for each task. By leveraging our adapted prefixes, our unified model achieves state-of-the-art or competitive performance on both zero-shot and supervised reasoning tasks, as demonstrated in extensive experiments


pdf bib
ClarET: Pre-training a Correlation-Aware Context-To-Event Transformer for Event-Centric Generation and Classification
Yucheng Zhou | Tao Shen | Xiubo Geng | Guodong Long | Daxin Jiang
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Generating new events given context with correlated ones plays a crucial role in many event-centric reasoning tasks. Existing works either limit their scope to specific scenarios or overlook event-level correlations. In this paper, we propose to pre-train a general Correlation-aware context-to-Event Transformer (ClarET) for event-centric reasoning. To achieve this, we propose three novel event-centric objectives, i.e., whole event recovering, contrastive event-correlation encoding and prompt-based event locating, which highlight event-level correlations with effective training. The proposed ClarET is applicable to a wide range of event-centric reasoning scenarios, considering its versatility of (i) event-correlation types (e.g., causal, temporal, contrast), (ii) application formulations (i.e., generation and classification), and (iii) reasoning types (e.g., abductive, counterfactual and ending reasoning). Empirical fine-tuning results, as well as zero- and few-shot learning, on 9 benchmarks (5 generation and 4 classification tasks covering 4 reasoning types with diverse event correlations), verify its effectiveness and generalization ability.

pdf bib
Reciprocal Learning of Knowledge Retriever and Response Ranker for Knowledge-Grounded Conversations
Jiazhan Feng | Chongyang Tao | Zhen Li | Chang Liu | Tao Shen | Dongyan Zhao
Proceedings of the 29th International Conference on Computational Linguistics

Grounding dialogue agents with knowledge documents has sparked increased attention in both academia and industry. Recently, a growing body of work is trying to build retrieval-based knowledge-grounded dialogue systems. While promising, these approaches require collecting pairs of dialogue context and the corresponding ground-truth knowledge sentences that contain the information regarding the dialogue context. Unfortunately, hand-labeling data to that end is time-consuming, and many datasets and applications lack such knowledge annotations. In this paper, we propose a reciprocal learning approach to jointly optimize a knowledge retriever and a response ranker for knowledge-grounded response retrieval without ground-truth knowledge labels. Specifically, the knowledge retriever uses the feedback from the response ranker as pseudo supervised signals of knowledge retrieval for updating its parameters, while the response ranker also receives the top-ranked knowledge sentences from knowledge retriever for optimization. Evaluation results on two public benchmarks show that our model can significantly outperform previous state-of-the-art methods.

pdf bib
Social Norms-Grounded Machine Ethics in Complex Narrative Situation
Tao Shen | Xiubo Geng | Daxin Jiang
Proceedings of the 29th International Conference on Computational Linguistics

Ethical judgment aims to determine if a person in a narrative situation acts under people’s social norms under a culture, so it is crucial to understand actions in narratives and achieve machine ethics. Recent works depend on data-driven methods to directly judge the ethics of complex real-world narratives but face two major challenges. First, they cannot well handle dilemma situations due to a lack of basic knowledge about social norms. Second, they focus merely on sparse situation-level judgment regardless of the social norms involved during the judgment, leading to a black box. In this work, inspired by previous knowledge-grounded and -augmented paradigms, we propose to complement a complex situation with grounded social norms. Besides a norm-grounding knowledge model, we present a novel norm-supported ethical judgment model in line with neural module networks to alleviate dilemma situations and improve norm-level explainability. Empirically, our model improves state-of-the-art performance on two narrative judgment benchmarks.

pdf bib
Hierarchical Relation-Guided Type-Sentence Alignment for Long-Tail Relation Extraction with Distant Supervision
Yang Li | Guodong Long | Tao Shen | Jing Jiang
Findings of the Association for Computational Linguistics: NAACL 2022

Distant supervision uses triple facts in knowledge graphs to label a corpus for relation extraction, leading to wrong labeling and long-tail problems. Some works use the hierarchy of relations for knowledge transfer to long-tail relations. However, a coarse-grained relation often implies only an attribute (e.g., domain or topic) of the distant fact, making it hard to discriminate relations based solely on sentence semantics. One solution is resorting to entity types, but open questions remain about how to fully leverage the information of entity types and how to align multi-granular entity types with sentences. In this work, we propose a novel model to enrich distantly-supervised sentences with entity types. It consists of (1) a pairwise type-enriched sentence encoding module injecting both context-free and -related backgrounds to alleviate sentence-level wrong labeling, and (2) a hierarchical type-sentence alignment module enriching a sentence with the triple fact’s basic attributes to support long-tail relations. Our model achieves new state-of-the-art results in overall and long-tail performance on benchmarks.

pdf bib
Rethinking Task-Specific Knowledge Distillation: Contextualized Corpus as Better Textbook
Chang Liu | Chongyang Tao | Jianxin Liang | Tao Shen | Jiazhan Feng | Quzhe Huang | Dongyan Zhao
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Knowledge distillation has been proven effective when customizing small language models for specific tasks. Here, a corpus as ‘textbook’ plays an indispensable role, only through which the teacher can teach the student. Prevailing methods adopt a two-stage distillation paradigm: general distillation first with task-agnostic general corpus and task-specific distillation next with augmented task-specific corpus. We argue that such a paradigm may not be optimal. In general distillation, it’s extravagant to let the diverse but desultory general knowledge overwhelms the limited model capacity of the student. While in task-specific distillation, the task corpus is usually limited and narrow, preventing the student from learning enough knowledge. To mitigate the issues in the two gapped corpora, we present a better textbook for the student to learn: contextualized corpus that contextualizes task corpus with large-scale general corpus through relevance-based text retrieval. Experimental results on GLUE benchmark demonstrate that contextualized corpus is the better textbook compared with jointly using general corpus and augmented task-specific corpus. Surprisingly, it enables task-specific distillation from scratch without general distillation while maintaining comparable performance, making it more flexible to customize the student model with desired model size under various computation constraints.

pdf bib
PCL: Peer-Contrastive Learning with Diverse Augmentations for Unsupervised Sentence Embeddings
Qiyu Wu | Chongyang Tao | Tao Shen | Can Xu | Xiubo Geng | Daxin Jiang
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Learning sentence embeddings in an unsupervised manner is fundamental in natural language processing. Recent common practice is to couple pre-trained language models with unsupervised contrastive learning, whose success relies on augmenting a sentence with a semantically-close positive instance to construct contrastive pairs. Nonetheless, existing approaches usually depend on a mono-augmenting strategy, which causes learning shortcuts towards the augmenting biases and thus corrupts the quality of sentence embeddings. A straightforward solution is resorting to more diverse positives from a multi-augmenting strategy, while an open question remains about how to unsupervisedly learn from the diverse positives but with uneven augmenting qualities in the text field. As one answer, we propose a novel Peer-Contrastive Learning (PCL) with diverse augmentations. PCL constructs diverse contrastive positives and negatives at the group level for unsupervised sentence embeddings. PCL performs peer-positive contrast as well as peer-network cooperation, which offers an inherent anti-bias ability and an effective way to learn from diverse augmentations. Experiments on STS benchmarks verify the effectiveness of PCL against its competitors in unsupervised sentence embeddings.


pdf bib
Improving Zero-Shot Cross-lingual Transfer for Multilingual Question Answering over Knowledge Graph
Yucheng Zhou | Xiubo Geng | Tao Shen | Wenqiang Zhang | Daxin Jiang
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Multilingual question answering over knowledge graph (KGQA) aims to derive answers from a knowledge graph (KG) for questions in multiple languages. To be widely applicable, we focus on its zero-shot transfer setting. That is, we can only access training data in a high-resource language, while need to answer multilingual questions without any labeled data in target languages. A straightforward approach is resorting to pre-trained multilingual models (e.g., mBERT) for cross-lingual transfer, but there is a still significant gap of KGQA performance between source and target languages. In this paper, we exploit unsupervised bilingual lexicon induction (BLI) to map training questions in source language into those in target language as augmented training data, which circumvents language inconsistency between training and inference. Furthermore, we propose an adversarial learning strategy to alleviate syntax-disorder of the augmented data, making the model incline to both language- and syntax-independence. Consequently, our model narrows the gap in zero-shot cross-lingual transfer. Experiments on two multilingual KGQA datasets with 11 zero-resource languages verify its effectiveness.

pdf bib
Modeling Event-Pair Relations in External Knowledge Graphs for Script Reasoning
Yucheng Zhou | Xiubo Geng | Tao Shen | Jian Pei | Wenqiang Zhang | Daxin Jiang
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf bib
Eliminating Sentiment Bias for Aspect-Level Sentiment Classification with Unsupervised Opinion Extraction
Bo Wang | Tao Shen | Guodong Long | Tianyi Zhou | Yi Chang
Findings of the Association for Computational Linguistics: EMNLP 2021

Aspect-level sentiment classification (ALSC) aims at identifying the sentiment polarity of a specified aspect in a sentence. ALSC is a practical setting in aspect-based sentiment analysis due to no opinion term labeling needed, but it fails to interpret why a sentiment polarity is derived for the aspect. To address this problem, recent works fine-tune pre-trained Transformer encoders for ALSC to extract an aspect-centric dependency tree that can locate the opinion words. However, the induced opinion words only provide an intuitive cue far below human-level interpretability. Besides, the pre-trained encoder tends to internalize an aspect’s intrinsic sentiment, causing sentiment bias and thus affecting model performance. In this paper, we propose a span-based anti-bias aspect representation learning framework. It first eliminates the sentiment bias in the aspect embedding by adversarial learning against aspects’ prior sentiment. Then, it aligns the distilled opinion candidates with the aspect by span-based dependency modeling to highlight the interpretable opinion terms. Our method achieves new state-of-the-art performance on five benchmarks, with the capability of unsupervised opinion extraction.


pdf bib
RatE: Relation-Adaptive Translating Embedding for Knowledge Graph Completion
Hao Huang | Guodong Long | Tao Shen | Jing Jiang | Chengqi Zhang
Proceedings of the 28th International Conference on Computational Linguistics

Many graph embedding approaches have been proposed for knowledge graph completion via link prediction. Among those, translating embedding approaches enjoy the advantages of light-weight structure, high efficiency and great interpretability. Especially when extended to complex vector space, they show the capability in handling various relation patterns including symmetry, antisymmetry, inversion and composition. However, previous translating embedding approaches defined in complex vector space suffer from two main issues: 1) representing and modeling capacities of the model are limited by the translation function with rigorous multiplication of two complex numbers; and 2) embedding ambiguity caused by one-to-many relations is not explicitly alleviated. In this paper, we propose a relation-adaptive translation function built upon a novel weighted product in complex space, where the weights are learnable, relation-specific and independent to embedding size. The translation function only requires eight more scalar parameters each relation, but improves expressive power and alleviates embedding ambiguity problem. Based on the function, we then present our Relation-adaptive translating Embedding (RatE) approach to score each graph triple. Moreover, a novel negative sampling method is proposed to utilize both prior knowledge and self-adversarial learning for effective optimization. Experiments verify RatE achieves state-of-the-art performance on four link prediction benchmarks.

pdf bib
Improving Long-Tail Relation Extraction with Collaborating Relation-Augmented Attention
Yang Li | Tao Shen | Guodong Long | Jing Jiang | Tianyi Zhou | Chengqi Zhang
Proceedings of the 28th International Conference on Computational Linguistics

Wrong labeling problem and long-tail relations are two main challenges caused by distant supervision in relation extraction. Recent works alleviate the wrong labeling by selective attention via multi-instance learning, but cannot well handle long-tail relations even if hierarchies of the relations are introduced to share knowledge. In this work, we propose a novel neural network, Collaborating Relation-augmented Attention (CoRA), to handle both the wrong labeling and long-tail relations. Particularly, we first propose relation-augmented attention network as base model. It operates on sentence bag with a sentence-to-relation attention to minimize the effect of wrong labeling. Then, facilitated by the proposed base model, we introduce collaborating relation features shared among relations in the hierarchies to promote the relation-augmenting process and balance the training data for long-tail relations. Besides the main training objective to predict the relation of a sentence bag, an auxiliary objective is utilized to guide the relation-augmenting process for a more accurate bag-level representation. In the experiments on the popular benchmark dataset NYT, the proposed CoRA improves the prior state-of-the-art performance by a large margin in terms of Precision@N, AUC and Hits@K. Further analyses verify its superior capability in handling long-tail relations in contrast to the competitors.

pdf bib
Exploiting Structured Knowledge in Text via Graph-Guided Representation Learning
Tao Shen | Yi Mao | Pengcheng He | Guodong Long | Adam Trischler | Weizhu Chen
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

In this work, we aim at equipping pre-trained language models with structured knowledge. We present two self-supervised tasks learning over raw text with the guidance from knowledge graphs. Building upon entity-level masked language models, our first contribution is an entity masking scheme that exploits relational knowledge underlying the text. This is fulfilled by using a linked knowledge graph to select informative entities and then masking their mentions. In addition, we use knowledge graphs to obtain distractors for the masked entities, and propose a novel distractor-suppressed ranking objective that is optimized jointly with masked language model. In contrast to existing paradigms, our approach uses knowledge graphs implicitly, only during pre-training, to inject language models with structured knowledge via learning from raw text. It is more efficient than retrieval-based methods that perform entity linking and integration during finetuning and inference, and generalizes more effectively than the methods that directly learn from concatenated graph triples. Experiments show that our proposed model achieves improved performance on five benchmarks, including question answering and knowledge base completion.


pdf bib
Tensorized Self-Attention: Efficiently Modeling Pairwise and Global Dependencies Together
Tao Shen | Tianyi Zhou | Guodong Long | Jing Jiang | Chengqi Zhang
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

Neural networks equipped with self-attention have parallelizable computation, light-weight structure, and the ability to capture both long-range and local dependencies. Further, their expressive power and performance can be boosted by using a vector to measure pairwise dependency, but this requires to expand the alignment matrix to a tensor, which results in memory and computation bottlenecks. In this paper, we propose a novel attention mechanism called “Multi-mask Tensorized Self-Attention” (MTSA), which is as fast and as memory-efficient as a CNN, but significantly outperforms previous CNN-/RNN-/attention-based models. MTSA 1) captures both pairwise (token2token) and global (source2token) dependencies by a novel compatibility function composed of dot-product and additive attentions, 2) uses a tensor to represent the feature-wise alignment scores for better expressive power but only requires parallelizable matrix multiplications, and 3) combines multi-head with multi-dimensional attentions, and applies a distinct positional mask to each head (subspace), so the memory and computation can be distributed to multiple heads, each with sequential information encoded independently. The experiments show that a CNN/RNN-free model based on MTSA achieves state-of-the-art or competitive performance on nine NLP benchmarks with compelling memory- and time-efficiency.

pdf bib
Multi-Task Learning for Conversational Question Answering over a Large-Scale Knowledge Base
Tao Shen | Xiubo Geng | Tao Qin | Daya Guo | Duyu Tang | Nan Duan | Guodong Long | Daxin Jiang
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

We consider the problem of conversational question answering over a large-scale knowledge base. To handle huge entity vocabulary of a large-scale knowledge base, recent neural semantic parsing based approaches usually decompose the task into several subtasks and then solve them sequentially, which leads to following issues: 1) errors in earlier subtasks will be propagated and negatively affect downstream ones; and 2) each subtask cannot naturally share supervision signals with others. To tackle these issues, we propose an innovative multi-task learning framework where a pointer-equipped semantic parsing model is designed to resolve coreference in conversations, and naturally empower joint learning with a novel type-aware entity detection model. The proposed framework thus enables shared supervisions and alleviates the effect of error propagation. Experiments on a large-scale conversational question answering dataset containing 1.6M question answering pairs over 12.8M entities show that the proposed framework improves overall F1 score from 67% to 79% compared with previous state-of-the-art work.