Wenhao Yu


2023

pdf bib
Large Language Models are Built-in Autoregressive Search Engines
Noah Ziems | Wenhao Yu | Zhihan Zhang | Meng Jiang
Findings of the Association for Computational Linguistics: ACL 2023

Document retrieval is a key stage of standard Web search engines. Existing dual-encoder dense retrievers obtain representations for questions and documents independently, allowing for only shallow interactions between them. To overcome this limitation, recent autoregressive search engines replace the dual-encoder architecture by directly generating identifiers for relevant documents in the candidate pool. However, the training cost of such autoregressive search engines rises sharply as the number of candidate documents increases. In this paper, we find that large language models (LLMs) can follow human instructions to directly generate URLs for document retrieval. Surprisingly, when providing a few Query-URL pairs as in-context demonstrations, LLMs can generate Web URLs where nearly 90% of the corresponding documents contain correct answers to open-domain questions. In this way, LLMs can be thought of as built-in search engines, since they have not been explicitly trained to map questions to document identifiers. Experiments demonstrate that our method can consistently achieve better retrieval performance than existing retrieval approaches by a significant margin on three open-domain question answering benchmarks, under both zero and few-shot settings. The code for this work can be found at https://github.com/Ziems/llm-url.

pdf bib
A Survey of Multi-task Learning in Natural Language Processing: Regarding Task Relatedness and Training Methods
Zhihan Zhang | Wenhao Yu | Mengxia Yu | Zhichun Guo | Meng Jiang
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics

Multi-task learning (MTL) has become increasingly popular in natural language processing (NLP) because it improves the performance of related tasks by exploiting their commonalities and differences. Nevertheless, it is still not understood very well how multi-task learning can be implemented based on the relatedness of training tasks. In this survey, we review recent advances of multi-task learning methods in NLP, with the aim of summarizing them into two general multi-task training methods based on their task relatedness: (i) joint training and (ii) multi-step training. We present examples in various NLP downstream applications, summarize the task relationships and discuss future directions of this promising topic.

pdf bib
APOLLO: A Simple Approach for Adaptive Pretraining of Language Models for Logical Reasoning
Soumya Sanyal | Yichong Xu | Shuohang Wang | Ziyi Yang | Reid Pryzant | Wenhao Yu | Chenguang Zhu | Xiang Ren
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Logical reasoning over text is an important ability that requires understanding the semantics of the text and reasoning through them to arrive at correct inferences. Prior works on pretraining language models to improve the logical reasoning ability require complex processing of training data (e.g., aligning symbolic knowledge to text), yielding task-specific data augmentation that is not easy to adapt to any general text corpus. In this work, we propose APOLLO, a simple adaptive pretraining approach to improve the logical reasoning skills of language models. We select a subset of Wikipedia for adaptive pretraining using a set of logical inference keywords as filter words. Further, we propose two self-supervised loss functions for training. First, we modify the masked language modeling loss only to mask specific parts-of-speech words that likely require higher-order reasoning to predict them. Second, we propose a sentence-level classification loss that teaches the model to distinguish between entailment and contradiction types of sentences. The proposed pretraining paradigm is both simple and independent of task formats. We demonstrate the effectiveness of APOLLO by comparing it with prior baselines on two logical reasoning datasets. APOLLO performs comparably on ReClor and outperforms baselines on LogiQA.

pdf bib
A Survey of Deep Learning for Mathematical Reasoning
Pan Lu | Liang Qiu | Wenhao Yu | Sean Welleck | Kai-Wei Chang
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Mathematical reasoning is a fundamental aspect of human intelligence and is applicable in various fields, including science, engineering, finance, and everyday life. The development of artificial intelligence (AI) systems capable of solving math problems and proving theorems in language has garnered significant interest in the fields of machine learning and natural language processing. For example, mathematics serves as a testbed for aspects of reasoning that are challenging for powerful deep learning models, driving new algorithmic and modeling advances. On the other hand, recent advances in large-scale neural language models have opened up new benchmarks and opportunities to use deep learning for mathematical reasoning. In this survey paper, we review the key tasks, datasets, and methods at the intersection of mathematical reasoning and deep learning over the past decade. We also evaluate existing benchmarks and methods, and discuss future research directions in this domain.

2022

pdf bib
Diversifying Content Generation for Commonsense Reasoning with Mixture of Knowledge Graph Experts
Wenhao Yu | Chenguang Zhu | Lianhui Qin | Zhihan Zhang | Tong Zhao | Meng Jiang
Proceedings of the 2nd Workshop on Deep Learning on Graphs for Natural Language Processing (DLG4NLP 2022)

Generative commonsense reasoning (GCR) in natural language is to reason about the commonsense while generating coherent text. Recent years have seen a surge of interest in improving the generation quality of commonsense reasoning tasks. Nevertheless, these approaches have seldom investigated diversity in the GCR tasks, which aims to generate alternative explanations for a real-world situation or predict all possible outcomes. Diversifying GCR is challenging as it expects to generate multiple outputs that are not only semantically different but also grounded in commonsense knowledge. In this paper, we propose MoKGE, a novel method that diversifies the generative reasoning by a mixture of expert (MoE) strategy on commonsense knowledge graphs (KG). A set of knowledge experts seek diverse reasoning on KG to encourage various generation outputs. Empirical experiments demonstrated that MoKGE can significantly improve the diversity while achieving on par performance on accuracy on two GCR benchmarks, based on both automatic and human evaluations.

pdf bib
Retrieval-augmented Generation across Heterogeneous Knowledge
Wenhao Yu
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Student Research Workshop

Retrieval-augmented generation (RAG) methods have been receiving increasing attention from the NLP community and achieved state-of-the-art performance on many NLP downstream tasks. Compared with conventional pre-trained generation models, RAG methods have remarkable advantages such as easy knowledge acquisition, strong scalability, and low training cost. Although existing RAG models have been applied to various knowledge-intensive NLP tasks, such as open-domain QA and dialogue systems, most of the work has focused on retrieving unstructured text documents from Wikipedia. In this paper, I first elaborate on the current obstacles to retrieving knowledge from a single-source homogeneous corpus. Then, I demonstrate evidence from both existing literature and my experiments, and provide multiple solutions on retrieval-augmented generation methods across heterogeneous knowledge.

pdf bib
KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering
Donghan Yu | Chenguang Zhu | Yuwei Fang | Wenhao Yu | Shuohang Wang | Yichong Xu | Xiang Ren | Yiming Yang | Michael Zeng
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Current Open-Domain Question Answering (ODQA) models typically include a retrieving module and a reading module, where the retriever selects potentially relevant passages from open-source documents for a given question, and the reader produces an answer based on the retrieved passages. The recently proposed Fusion-in-Decoder (FiD) framework is a representative example, which is built on top of a dense passage retriever and a generative reader, achieving the state-of-the-art performance. In this paper we further improve the FiD approach by introducing a knowledge-enhanced version, namely KG-FiD. Our new model uses a knowledge graph to establish the structural relationship among the retrieved passages, and a graph neural network (GNN) to re-rank the passages and select only a top few for further processing. Our experiments on common ODQA benchmark datasets (Natural Questions and TriviaQA) demonstrate that KG-FiD can achieve comparable or better performance in answer prediction than FiD, with less than 40% of the computation cost.

pdf bib
Knowledge-Augmented Methods for Natural Language Processing
Chenguang Zhu | Yichong Xu | Xiang Ren | Bill Yuchen Lin | Meng Jiang | Wenhao Yu
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts

Knowledge in natural language processing (NLP) has been a rising trend especially after the advent of large scale pre-trained models. NLP models with attention to knowledge can i) access unlimited amount of external information; ii) delegate the task of storing knowledge from its parameter space to knowledge sources; iii) obtain up-to-date information; iv) make prediction results more explainable via selected knowledge. In this tutorial, we will introduce the key steps in integrating knowledge into NLP, including knowledge grounding from text, knowledge representation and fusing. In addition, we will introduce recent state-of-the-art applications in fusing knowledge into language understanding, language generation and commonsense reasoning.

pdf bib
A Unified Encoder-Decoder Framework with Entity Memory
Zhihan Zhang | Wenhao Yu | Chenguang Zhu | Meng Jiang
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Entities, as important carriers of real-world knowledge, play a key role in many NLP tasks. We focus on incorporating entity knowledge into an encoder-decoder framework for informative text generation. Existing approaches tried to index, retrieve, and read external documents as evidence, but they suffered from a large computational overhead. In this work, we propose an encoder-decoder framework with an entity memory, namely EDMem. The entity knowledge is stored in the memory as latent representations, and the memory is pre-trained on Wikipedia along with encoder-decoder parameters. To precisely generate entity names, we design three decoding methods to constrain entity generation by linking entities in the memory. EDMem is a unified framework that can be used on various entity-intensive question answering and generation tasks. Extensive experimental results show that EDMem outperforms both memory-based auto-encoder models and non-memory encoder-decoder models.

pdf bib
Retrieval Augmentation for Commonsense Reasoning: A Unified Approach
Wenhao Yu | Chenguang Zhu | Zhihan Zhang | Shuohang Wang | Zhuosheng Zhang | Yuwei Fang | Meng Jiang
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

A common thread of retrieval-augmented methods in the existing literature focuses on retrieving encyclopedic knowledge, such as Wikipedia, which facilitates well-defined entity and relation spaces that can be modeled. However, applying such methods to commonsense reasoning tasks faces two unique challenges, i.e., the lack of a general large-scale corpus for retrieval and a corresponding effective commonsense retriever. In this paper, we systematically investigate how to leverage commonsense knowledge retrieval to improve commonsense reasoning tasks. We proposed a unified framework of retrieval-augmented commonsense reasoning (called RACo), including a newly constructed commonsense corpus with over 20 million documents and novel strategies for training a commonsense retriever. We conducted experiments on four different commonsense reasoning tasks. Extensive evaluation results showed that our proposed RACo can significantly outperform other knowledge-enhanced method counterparts, achieving new SoTA performance on the CommonGen and CREAK leaderboards.

pdf bib
Empowering Language Models with Knowledge Graph Reasoning for Open-Domain Question Answering
Ziniu Hu | Yichong Xu | Wenhao Yu | Shuohang Wang | Ziyi Yang | Chenguang Zhu | Kai-Wei Chang | Yizhou Sun
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Answering open-domain questions requires world knowledge about in-context entities. As pre-trained Language Models (LMs) lack the power to store all required knowledge, external knowledge sources, such as knowledge graphs, are often used to augment LMs. In this work, we propose knOwledge REasOning empowered Language Model(OREO-LM), which consists of a novel Knowledge Interaction Layer that can be flexibly plugged into existing Transformer-based LMs to interact with a differentiable Knowledge Graph Reasoning module collaboratively. In this way, LM guides KG to walk towards the desired answer, while the retrieved knowledge improves LM.By adopting OREO-LM to RoBERTa and T5, we show significant performance gain, achieving state-of-art results in the Closed-Book setting. The performance enhancement is mainly from the KG reasoning’s capacity to infer missing relational facts. In addition, OREO-LM provides reasoning paths as rationales to interpret the model’s decision.

pdf bib
Diversifying Content Generation for Commonsense Reasoning with Mixture of Knowledge Graph Experts
Wenhao Yu | Chenguang Zhu | Lianhui Qin | Zhihan Zhang | Tong Zhao | Meng Jiang
Findings of the Association for Computational Linguistics: ACL 2022

Generative commonsense reasoning (GCR) in natural language is to reason about the commonsense while generating coherent text. Recent years have seen a surge of interest in improving the generation quality of commonsense reasoning tasks. Nevertheless, these approaches have seldom investigated diversity in the GCR tasks, which aims to generate alternative explanations for a real-world situation or predict all possible outcomes. Diversifying GCR is challenging as it expects to generate multiple outputs that are not only semantically different but also grounded in commonsense knowledge. In this paper, we propose MoKGE, a novel method that diversifies the generative reasoning by a mixture of expert (MoE) strategy on commonsense knowledge graphs (KG). A set of knowledge experts seek diverse reasoning on KG to encourage various generation outputs. Empirical experiments demonstrated that MoKGE can significantly improve the diversity while achieving on par performance on accuracy on two GCR benchmarks, based on both automatic and human evaluations.

pdf bib
Dict-BERT: Enhancing Language Model Pre-training with Dictionary
Wenhao Yu | Chenguang Zhu | Yuwei Fang | Donghan Yu | Shuohang Wang | Yichong Xu | Michael Zeng | Meng Jiang
Findings of the Association for Computational Linguistics: ACL 2022

Pre-trained language models (PLMs) aim to learn universal language representations by conducting self-supervised training tasks on large-scale corpora. Since PLMs capture word semantics in different contexts, the quality of word representations highly depends on word frequency, which usually follows a heavy-tailed distributions in the pre-training corpus. Therefore, the embeddings of rare words on the tail are usually poorly optimized. In this work, we focus on enhancing language model pre-training by leveraging definitions of the rare words in dictionaries (e.g., Wiktionary). To incorporate a rare word definition as a part of input, we fetch its definition from the dictionary and append it to the end of the input text sequence. In addition to training with the masked language modeling objective, we propose two novel self-supervised pre-training tasks on word and sentence-level alignment between input text sequence and rare word definitions to enhance language modeling representation with dictionary. We evaluate the proposed Dict-BERT model on the language understanding benchmark GLUE and eight specialized domain benchmark datasets. Extensive experiments demonstrate that Dict-BERT can significantly improve the understanding of rare words and boost model performance on various NLP downstream tasks.

pdf bib
Grape: Knowledge Graph Enhanced Passage Reader for Open-domain Question Answering
Mingxuan Ju | Wenhao Yu | Tong Zhao | Chuxu Zhang | Yanfang Ye
Findings of the Association for Computational Linguistics: EMNLP 2022

A common thread of open-domain question answering (QA) models employs a retriever-reader pipeline that first retrieves a handful of relevant passages from Wikipedia and then peruses the passages to produce an answer. However, even state-of-the-art readers fail to capture the complex relationships between entities appearing in questions and retrieved passages, leading to answers that contradict the facts. In light of this, we propose a novel knowledge graph enhanced passage reader, namely Grape, to improve the reader performance for open-domain QA. Specifically, for each pair of question and retrieved passage, we first construct a localized bipartite graph, attributed to entity embeddings extracted from the intermediate layer of the reader model. Then, a graph neural network learns relational knowledge while fusing graph and contextual representations into the hidden states of the reader model. Experiments on three open-domain QA benchmarks show Grape can improve the state-of-the-art performance by up to 2.2 exact match score with a negligible overhead increase, with the same retriever and retrieved passages. Our code is publicly available at https://github.com/jumxglhf/GRAPE.

pdf bib
Task Compass: Scaling Multi-task Pre-training with Task Prefix
Zhuosheng Zhang | Shuohang Wang | Yichong Xu | Yuwei Fang | Wenhao Yu | Yang Liu | Hai Zhao | Chenguang Zhu | Michael Zeng
Findings of the Association for Computational Linguistics: EMNLP 2022

Leveraging task-aware annotated data as supervised signals to assist with self-supervised learning on large-scale unlabeled data has become a new trend in pre-training language models. Existing studies show that multi-task learning with large-scale supervised tasks suffers from negative effects across tasks. To tackle the challenge, we propose a task prefix guided multi-task pre-training framework to explore the relationships among tasks. We conduct extensive experiments on 40 datasets, which show that our model can not only serve as the strong foundation backbone for a wide range of tasks but also be feasible as a probing tool for analyzing task relationships. The task relationships reflected by the prefixes align transfer learning performance between tasks. They also suggest directions for data augmentation with complementary tasks, which help our model achieve human-parity results on commonsense reasoning leaderboards. Code is available at https://github.com/cooelf/CompassMTL.

2021

pdf bib
Validating Label Consistency in NER Data Annotation
Qingkai Zeng | Mengxia Yu | Wenhao Yu | Tianwen Jiang | Meng Jiang
Proceedings of the 2nd Workshop on Evaluation and Comparison of NLP Systems

Data annotation plays a crucial role in ensuring your named entity recognition (NER) projects are trained with the right information to learn from. Producing the most accurate labels is a challenge due to the complexity involved with annotation. Label inconsistency between multiple subsets of data annotation (e.g., training set and test set, or multiple training subsets) is an indicator of label mistakes. In this work, we present an empirical method to explore the relationship between label (in-)consistency and NER model performance. It can be used to validate the label consistency (or catches the inconsistency) in multiple sets of NER data annotation. In experiments, our method identified the label inconsistency of test data in SCIERC and CoNLL03 datasets (with 26.7% and 5.4% label mistakes). It validated the consistency in the corrected version of both datasets.

pdf bib
Technical Question Answering across Tasks and Domains
Wenhao Yu | Lingfei Wu | Yu Deng | Qingkai Zeng | Ruchi Mahindru | Sinem Guven | Meng Jiang
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Papers

Building automatic technical support system is an important yet challenge task. Conceptually, to answer a user question on a technical forum, a human expert has to first retrieve relevant documents, and then read them carefully to identify the answer snippet. Despite huge success the researchers have achieved in coping with general domain question answering (QA), much less attentions have been paid for investigating technical QA. Specifically, existing methods suffer from several unique challenges (i) the question and answer rarely overlaps substantially and (ii) very limited data size. In this paper, we propose a novel framework of deep transfer learning to effectively address technical QA across tasks and domains. To this end, we present an adjustable joint learning approach for document retrieval and reading comprehension tasks. Our experiments on the TechQA demonstrates superior performance compared with state-of-the-art methods.

pdf bib
Injecting Entity Types into Entity-Guided Text Generation
Xiangyu Dong | Wenhao Yu | Chenguang Zhu | Meng Jiang
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Recent successes in deep generative modeling have led to significant advances in natural language generation (NLG). Incorporating entities into neural generation models has demonstrated great improvements by assisting to infer the summary topic and to generate coherent content. To enhance the role of entity in NLG, in this paper, we aim to model the entity type in the decoding phase to generate contextual words accurately. We develop a novel NLG model to produce a target sequence based on a given list of entities. Our model has a multi-step decoder that injects the entity types into the process of entity mention generation. Experiments on two public news datasets demonstrate type injection performs better than existing type embedding concatenation baselines.

pdf bib
Sentence-Permuted Paragraph Generation
Wenhao Yu | Chenguang Zhu | Tong Zhao | Zhichun Guo | Meng Jiang
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Generating paragraphs of diverse contents is important in many applications. Existing generation models produce similar contents from homogenized contexts due to the fixed left-to-right sentence order. Our idea is permuting the sentence orders to improve the content diversity of multi-sentence paragraph. We propose a novel framework PermGen whose objective is to maximize the expected log-likelihood of output paragraph distributions with respect to all possible sentence orders. PermGen uses hierarchical positional embedding and designs new procedures for training, and decoding in the sentence-permuted generation. Experiments on three paragraph generation benchmarks demonstrate PermGen generates more diverse outputs with a higher quality than existing models.

pdf bib
Knowledge-Enriched Natural Language Generation
Wenhao Yu | Meng Jiang | Zhiting Hu | Qingyun Wang | Heng Ji | Nazneen Rajani
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: Tutorial Abstracts

Knowledge-enriched text generation poses unique challenges in modeling and learning, driving active research in several core directions, ranging from integrated modeling of neural representations and symbolic information in the sequential/hierarchical/graphical structures, learning without direct supervisions due to the cost of structured annotation, efficient optimization and inference with massive and global constraints, to language grounding on multiple modalities, and generative reasoning with implicit commonsense knowledge and background knowledge. In this tutorial we will present a roadmap to line up the state-of-the-art methods to tackle these challenges on this cutting-edge problem. We will dive deep into various technical components: how to represent knowledge, how to feed knowledge into a generation model, how to evaluate generation results, and what are the remaining challenges?

2020

pdf bib
Tri-Train: Automatic Pre-Fine Tuning between Pre-Training and Fine-Tuning for SciNER
Qingkai Zeng | Wenhao Yu | Mengxia Yu | Tianwen Jiang | Tim Weninger | Meng Jiang
Findings of the Association for Computational Linguistics: EMNLP 2020

The training process of scientific NER models is commonly performed in two steps: i) Pre-training a language model by self-supervised tasks on huge data and ii) fine-tune training with small labelled data. The success of the strategy depends on the relevance between the data domains and between the tasks. However, gaps are found in practice when the target domains are specific and small. We propose a novel framework to introduce a “pre-fine tuning” step between pre-training and fine-tuning. It constructs a corpus by selecting sentences from unlabeled documents that are the most relevant with the labelled training data. Instead of predicting tokens in random spans, the pre-fine tuning task is to predict tokens in entity candidates identified by text mining methods. Pre-fine tuning is automatic and light-weight because the corpus size can be much smaller than pre-training data to achieve a better performance. Experiments on seven benchmarks demonstrate the effectiveness.

pdf bib
Crossing Variational Autoencoders for Answer Retrieval
Wenhao Yu | Lingfei Wu | Qingkai Zeng | Shu Tao | Yu Deng | Meng Jiang
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Answer retrieval is to find the most aligned answer from a large set of candidates given a question. Learning vector representations of questions/answers is the key factor. Question-answer alignment and question/answer semantics are two important signals for learning the representations. Existing methods learned semantic representations with dual encoders or dual variational auto-encoders. The semantic information was learned from language models or question-to-question (answer-to-answer) generative processes. However, the alignment and semantics were too separate to capture the aligned semantics between question and answer. In this work, we propose to cross variational auto-encoders by generating questions with aligned answers and generating answers with aligned questions. Experiments show that our method outperforms the state-of-the-art answer retrieval method on SQuAD.

pdf bib
A Technical Question Answering System with Transfer Learning
Wenhao Yu | Lingfei Wu | Yu Deng | Ruchi Mahindru | Qingkai Zeng | Sinem Guven | Meng Jiang
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations

In recent years, the need for community technical question-answering sites has increased significantly. However, it is often expensive for human experts to provide timely and helpful responses on those forums. We develop TransTQA, which is a novel system that offers automatic responses by retrieving proper answers based on correctly answered similar questions in the past. TransTQA is built upon a siamese ALBERT network, which enables it to respond quickly and accurately. Furthermore, TransTQA adopts a standard deep transfer learning strategy to improve its capability of supporting multiple technical domains.

2019

pdf bib
Faceted Hierarchy: A New Graph Type to Organize Scientific Concepts and a Construction Method
Qingkai Zeng | Mengxia Yu | Wenhao Yu | JinJun Xiong | Yiyu Shi | Meng Jiang
Proceedings of the Thirteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-13)

On a scientific concept hierarchy, a parent concept may have a few attributes, each of which has multiple values being a group of child concepts. We call these attributes facets: classification has a few facets such as application (e.g., face recognition), model (e.g., svm, knn), and metric (e.g., precision). In this work, we aim at building faceted concept hierarchies from scientific literature. Hierarchy construction methods heavily rely on hypernym detection, however, the faceted relations are parent-to-child links but the hypernym relation is a multi-hop, i.e., ancestor-to-descendent link with a specific facet “type-of”. We use information extraction techniques to find synonyms, sibling concepts, and ancestor-descendent relations from a data science corpus. And we propose a hierarchy growth algorithm to infer the parent-child links from the three types of relationships. It resolves conflicts by maintaining the acyclic structure of a hierarchy.