To protect users from massive hateful content, existing works studied automated hate speech detection. Despite the existing efforts, one question remains: Do automated hate speech detectors conform to social media content policies? A platform’s content policies are a checklist of content moderated by the social media platform. Because content moderation rules are often uniquely defined, existing hate speech datasets cannot directly answer this question. This work seeks to answer this question by creating HateModerate, a dataset for testing the behaviors of automated content moderators against content policies. First, we engage 28 annotators and GPT in a six-step annotation process, resulting in a list of hateful and non-hateful test suites matching each of Facebook’s 41 hate speech policies. Second, we test the performance of state-of-the-art hate speech detectors against HateModerate, revealing substantial failures these models have in their conformity to the policies. Third, using HateModerate, we augment the training data of a top-downloaded hate detector on HuggingFace. We observe significant improvement in the models’ conformity to content policies while having comparable scores on the original test data. Our dataset and code can be found on https://github.com/stevens-textmining/HateModerate.

Despite much success in natural language processing (NLP), pre-trained language models typically lead to a high computational cost during inference. Multi-exit is a mainstream approach to address this issue by making a trade-off between efficiency and accuracy, where the saving of computation comes from an early exit. However, whether such saving from early-exiting is robust remains unknown. Motivated by this, we first show that directly adapting existing adversarial attack approaches targeting model accuracy cannot significantly reduce inference efficiency. To this end, we propose a simple yet effective attacking framework, SAME, a novel slowdown attack framework on multi-exit models, which is specially tailored to reduce the efficiency of the multi-exit models. By leveraging the multi-exit models’ design characteristics, we utilize all internal predictions to guide the adversarial sample generation instead of merely considering the final prediction. Experiments on the GLUE benchmark show that SAME can effectively diminish the efficiency gain of various multi-exit models by 80% on average, convincingly validating its effectiveness and generalization ability.

The recently proposed capability-based NLP testing allows model developers to test the functional capabilities of NLP models, revealing functional failures for models with good held-out evaluation scores. However, existing work on capability-based testing requires the developer to compose each individual test template from scratch. Such approach thus requires extensive manual efforts and is less scalable. In this paper, we investigate a different approach that requires the developer to only annotate a few test templates, while leveraging the GPT-3 engine to generate the majority of test cases. While our approach saves the manual efforts by design, it guarantees the correctness of the generated suites with a validity checker. Moreover, our experimental results show that the test suites generated by GPT-3 are more diverse than the manually created ones; they can also be used to detect more errors compared to manually created counterparts. Our test suites can be downloaded at https://anonymous-researcher-nlp.github.io/testaug/.

It is a common belief that training deep transformers from scratch requires large datasets. Consequently, for small datasets, people usually use shallow and simple additional layers on top of pre-trained models during fine-tuning. This work shows that this does not always need to be the case: with proper initialization and optimization, the benefits of very deep transformers can carry over to challenging tasks with small datasets, including Text-to-SQL semantic parsing and logical reading comprehension. In particular, we successfully train 48 layers of transformers, comprising 24 fine-tuned layers from pre-trained RoBERTa and 24 relation-aware layers trained from scratch. With fewer training steps and no task-specific pre-training, we obtain the state of the art performance on the challenging cross-domain Text-to-SQL parsing benchmark Spider. We achieve this by deriving a novel Data dependent Transformer Fixed-update initialization scheme (DT-Fixup), inspired by the prior T-Fixup work. Further error analysis shows that increasing depth can help improve generalization on small datasets for hard cases that require reasoning and structural understanding.

A natural language database interface (NLDB) can democratize data-driven insights for non-technical users. However, existing Text-to-SQL semantic parsers cannot achieve high enough accuracy in the cross-database setting to allow good usability in practice. This work presents TURING, a NLDB system toward bridging this gap. The cross-domain semantic parser of TURING with our novel value prediction method achieves 75.1% execution accuracy, and 78.3% top-5 beam execution accuracy on the Spider validation set (Yu et al., 2018b). To benefit from the higher beam accuracy, we design an interactive system where the SQL hypotheses in the beam are explained step-by-step in natural language, with their differences highlighted. The user can then compare and judge the hypotheses to select which one reflects their intention if any. The English explanations of SQL queries in TURING are produced by our high-precision natural language generation system based on synchronous grammars.

In this paper, we propose a globally normalized model for context-free grammar (CFG)-based semantic parsing. Instead of predicting a probability, our model predicts a real-valued score at each step and does not suffer from the label bias problem. Experiments show that our approach outperforms locally normalized models on small datasets, but it does not yield improvement on a large dataset.

Consumers dissatisfied with the normal dispute resolution process provided by an e-commerce company’s customer service agents have the option of escalating their complaints by filing grievances with a government authority. This paper tackles the challenge of monitoring ongoing text chat dialogues to identify cases where the customer expresses such an intent, providing triage and prioritization for a separate pool of specialized agents specially trained to handle more complex situations. We describe a hybrid model that tackles this challenge by integrating recurrent neural networks with manually-engineered features. Experiments show that both components are complementary and contribute to overall recall, outperforming competitive baselines. A trial online deployment of our model demonstrates its business value in improving customer service.

We demonstrate an end-to-end question answering system that integrates BERT with the open-source Anserini information retrieval toolkit. In contrast to most question answering and reading comprehension models today, which operate over small amounts of input text, our system integrates best practices from IR with a BERT-based reader to identify answers from a large corpus of Wikipedia articles in an end-to-end fashion. We report large improvements over previous results on a standard benchmark test collection, showing that fine-tuning pretrained BERT with SQuAD is sufficient to achieve high accuracy in identifying answer spans.

Semantic similarity modeling is central to many NLP problems such as natural language inference and question answering. Syntactic structures interact closely with semantics in learning compositional representations and alleviating long-range dependency issues. How-ever, such structure priors have not been well exploited in previous work for semantic mod-eling. To examine their effectiveness, we start with the Pairwise Word Interaction Model, one of the best models according to a recent reproducibility study, then introduce components for modeling context and structure using multi-layer BiLSTMs and TreeLSTMs. In addition, we introduce residual connections to the deep convolutional neural network component of the model. Extensive evaluations on eight benchmark datasets show that incorporating structural information contributes to consistent improvements over strong baselines.

This paper applies BERT to ad hoc document retrieval on news articles, which requires addressing two challenges: relevance judgments in existing test collections are typically provided only at the document level, and documents often exceed the length that BERT was designed to handle. Our solution is to aggregate sentence-level evidence to rank documents. Furthermore, we are able to leverage passage-level relevance judgments fortuitously available in other domains to fine-tune BERT models that are able to capture cross-domain notions of relevance, and can be directly used for ranking news articles. Our simple neural ranking models achieve state-of-the-art effectiveness on three standard test collections.

A core problem of information retrieval (IR) is relevance matching, which is to rank documents by relevance to a user’s query. On the other hand, many NLP problems, such as question answering and paraphrase identification, can be considered variants of semantic matching, which is to measure the semantic distance between two pieces of short texts. While at a high level both relevance and semantic matching require modeling textual similarity, many existing techniques for one cannot be easily adapted to the other. To bridge this gap, we propose a novel model, HCAN (Hybrid Co-Attention Network), that comprises (1) a hybrid encoder module that includes ConvNet-based and LSTM-based encoders, (2) a relevance matching module that measures soft term matches with importance weighting at multiple granularities, and (3) a semantic matching module with co-attention mechanisms that capture context-aware semantic relatedness. Evaluations on multiple IR and NLP benchmarks demonstrate state-of-the-art effectiveness compared to approaches that do not exploit pretraining on external data. Extensive ablation studies suggest that relevance and semantic matching signals are complementary across many problem settings, regardless of the choice of underlying encoders.

We present Birch, a system that applies BERT to document retrieval via integration with the open-source Anserini information retrieval toolkit to demonstrate end-to-end search over large document collections. Birch implements simple ranking models that achieve state-of-the-art effectiveness on standard TREC newswire and social media test collections. This demonstration focuses on technical challenges in the integration of NLP and IR capabilities, along with the design rationale behind our approach to tightly-coupled integration between Python (to support neural networks) and the Java Virtual Machine (to support document retrieval using the open-source Lucene search library). We demonstrate integration of Birch with an existing search interface as well as interactive notebooks that highlight its capabilities in an easy-to-understand manner.

In this paper, we describe our Neural Machine Translation (NMT) systems for the WAT 2019 translation tasks we focus on. This year we participate in scientific paper tasks and focus on the language pair between English and Japanese. We use Transformer model through our work in this paper to explore and experience the powerful of the Transformer architecture relying on self-attention mechanism. We use different NMT toolkit/library as the implementation of training the Transformer model. For word segmentation, we use different subword segmentation strategies while using different toolkit/library. We not only give the translation accuracy obtained based on absolute position encodings that introduced in the Transformer model, but also report the the improvements in translation accuracy while replacing absolute position encodings with relative position representations. We also ensemble several independent trained Transformer models to further improve the translation accuracy.

We tackle the problem of context reconstruction in Chinese dialogue, where the task is to replace pronouns, zero pronouns, and other referring expressions with their referent nouns so that sentences can be processed in isolation without context. Following a standard decomposition of the context reconstruction task into referring expression detection and coreference resolution, we propose a novel end-to-end architecture for separately and jointly accomplishing this task. Key features of this model include POS and position encoding using CNNs and a novel pronoun masking mechanism. One perennial problem in building such models is the paucity of training data, which we address by augmenting previously-proposed methods to generate a large amount of realistic training data. The combination of more data and better models yields accuracy higher than the state-of-the-art method in coreference resolution and end-to-end context reconstruction.

Traditional word embedding approaches learn semantic information at word level while ignoring the meaningful internal structures of words like morphemes. Furthermore, existing morphology-based models directly incorporate morphemes to train word embeddings, but still neglect the latent meanings of morphemes. In this paper, we explore to employ the latent meanings of morphological compositions of words to train and enhance word embeddings. Based on this purpose, we propose three Latent Meaning Models (LMMs), named LMM-A, LMM-S and LMM-M respectively, which adopt different strategies to incorporate the latent meanings of morphemes during the training process. Experiments on word similarity, syntactic analogy and text classification are conducted to validate the feasibility of our models. The results demonstrate that our models outperform the baselines on five word similarity datasets. On Wordsim-353 and RG-65 datasets, our models nearly achieve 5% and 7% gains over the classic CBOW model, respectively. For the syntactic analogy and text classification tasks, our models also surpass all the baselines including a morphology-based model.

Recent research proposes syntax-based approaches to address the problem of generating programs from natural language specifications. These approaches typically train a sequence-to-sequence learning model using a syntax-based objective: maximum likelihood estimation (MLE). Such syntax-based approaches do not effectively address the goal of generating semantically correct programs, because these approaches fail to handle Program Aliasing, i.e., semantically equivalent programs may have many syntactically different forms. To address this issue, in this paper, we propose a semantics-based approach named SemRegex. SemRegex provides solutions for a subtask of the program-synthesis problem: generating regular expressions from natural language. Different from the existing syntax-based approaches, SemRegex trains the model by maximizing the expected semantic correctness of the generated regular expressions. The semantic correctness is measured using the DFA-equivalence oracle, random test cases, and distinguishing test cases. The experiments on three public datasets demonstrate the superiority of SemRegex over the existing state-of-the-art approaches.

We propose a novel framework based on neural networks to identify the sentiment of opinion targets in a comment/review. Our framework adopts multiple-attention mechanism to capture sentiment features separated by a long distance, so that it is more robust against irrelevant information. The results of multiple attentions are non-linearly combined with a recurrent neural network, which strengthens the expressive power of our model for handling more complications. The weighted-memory mechanism not only helps us avoid the labor-intensive feature engineering work, but also provides a tailor-made memory for different opinion targets of a sentence. We examine the merit of our model on four datasets: two are from SemEval2014, i.e. reviews of restaurants and laptops; a twitter dataset, for testing its performance on social media data; and a Chinese news comment dataset, for testing its language sensitivity. The experimental results show that our model consistently outperforms the state-of-the-art methods on different types of data.

Learning word embeddings has received a significant amount of attention recently. Often, word embeddings are learned in an unsupervised manner from a large collection of text. The genre of the text typically plays an important role in the effectiveness of the resulting embeddings. How to effectively train word embedding models using data from different domains remains a problem that is less explored. In this paper, we present a simple yet effective method for learning word embeddings based on text from different domains. We demonstrate the effectiveness of our approach through extensive experiments on various down-stream NLP tasks.

Unlike European languages, many Asian languages like Chinese and Japanese do not have typographic boundaries in written system. Word segmentation (tokenization) that break sentences down into individual words (tokens) is normally treated as the first step for machine translation (MT). For Chinese and Japanese, different rules and segmentation tools lead different segmentation results in different level of granularity between Chinese and Japanese. To improve the translation accuracy, we adjust and balance the granularity of segmentation results around terms for Chinese–Japanese patent corpus for training translation model. In this paper, we describe a statistical machine translation (SMT) system which is built on re-tokenized Chinese-Japanese patent training corpus using extracted bilingual multi-word terms.