Articles

Traditional toxicity detection models have fo- cused on the single utterance level without deeper understanding of context. We introduce CONDA, a new dataset for in-game toxic lan- guage detection enabling joint intent classifi- cation and slot filling analysis, which is the core task of Natural Language Understanding (NLU). The dataset …...

Scheduled sampling is an effective method to alleviate the exposure bias problem of neu- ral machine translation. It simulates the in- ference scene by randomly replacing ground- truth target input tokens with predicted ones during training. Despite its success, its crit- ical schedule strategies are merely based on training steps, …...

Multi-target stance detection aims to identify the stance taken toward a pair of different tar- gets from the same text, and typically, there are multiple target pairs per dataset. Existing works generally train one model for each target pair. However, they fail to learn target-specific representations and are prone to …...

Interactive argument pair identification is es- sential in the context of dialogical argumenta- tion mining. Existing research treats it as a problem of sentence matching and largely re- lies on textual information to compute the sim- ilarities. However, the interaction of opinions usually involves the background of the topic and …...

Lifelong topic models mainly focus on in- domain text streams in which each chunk only contains documents from a single domain. To overcome data diversity of the in-domain cor- pus, most of the existing methods exploit the information from limited sources in a separate and heuristic manner. In this study, …...

Pre-trained transformer language models have shown remarkable performance on a variety of NLP tasks. However, recent research has suggested that phrase-level representations in these models reflect heavy influences of lexi- cal content, but lack evidence of sophisticated, compositional phrase information (Yu and Et- tinger, 2020). Here we investigate the impact …...

Table-to-text generation is a subtask of data- to-text generation which aims to generate nal- tural language text based on input table. Pre- training techniques have achieved great suc- cess on table-to-text generation. However, the pre-trained models used in previous works are typically trained on free-form natural language text while the …...

Chains for Science Questions Mokanarangan Thayaparan†, Marco Valentino†, Andr´e Freitas†‡ Department of Computer Science, University of Manchester, United Kingdom† Idiap Research Institute, Switzerland‡ {firstname.lastname}@manchester.ac.uk Abstract We propose an explainable inference approach for science questions by reasoning on ground- ing and abstract inference chains. This paper frames question answering as a …...

Present language understanding methods have demonstrated extraordinary ability of recog- nizing patterns in texts via machine learning. However, existing methods indiscriminately use the recognized patterns in the testing phase that is inherently different from us humans who have counterfactual thinking, e.g., to scru- tinize for the hard testing samples. Inspired …...

Having numerous potential applications and great impact, end-to-end speech translation (ST) has long been treated as an independent task, failing to fully draw strength from the rapid advances of its sibling - text machine translation (MT). With text and audio inputs represented differently, the modality gap has rendered MT data …...

We propose two fast neural combinatory mod- els for constituency parsing: binary and multi- branching. Our models decompose the bottom- up parsing process into 1) classification of tags, labels, and binary orientations or chunks and 2) vector composition based on the computed orientations or chunks. These models have theoretical sub-quadratic …...

A summary quality measure is judged by how well it correlates with quality scores produced by human annotators. A higher correlation with human scores is considered to be a deci- sive indicator of a better measure. In this work we present observations that cast doubt on this view. We also …...

An important aspect of developing dialogue systems is how to evaluate and compare the performance of different systems. Existing au- tomatic evaluation metrics are based on turn- level quality evaluation and use average scores for system-level comparison. In this paper, we propose to measure the performance of a di- alogue …...

Recently, dense passage retrieval has become a mainstream approach to finding relevant infor- mation in various natural language processing tasks. A number of studies have been devoted to improving the widely adopted dual-encoder architecture. However, most of the previous studies only consider query-centric similarity relation when learning the dual-encoder re- …...

Chinese spelling correction (CSC) is an im- portant yet challenging task. Existing state-of- the-art methods either only use a pre-trained language model or incorporate phonological information as external knowledge. In this paper, we propose a novel end-to-end CSC model that integrates phonetic features into language model by leveraging the powerful …...

Machine Reading Comprehension (MRC) aims to extract answers to questions given a passage, which has been widely studied recently especially in open domains. How- ever, few efforts have been made on closed- domain MRC, mainly due to the lack of large- scale training data. In this paper, we intro- duce …...

Current models for event causality identifica- tion (ECI) mainly adopt a supervised frame- work, which heavily rely on labeled data for training. Unfortunately, the scale of current annotated datasets is relatively limited, which cannot provide sufficient support for models to capture useful indicators from causal state- ments, especially for handing …...

Though being a primary trend for enhancing interpretability of neural networks, attention mechanism’s reliability and validity are still under debate. In this paper, we try to pu- rify attention scores to obtain a more faithful explanation of downstream models. Specifi- cally, we propose a framework consisting of a learner and …...

We generalize deep self-attention distillation in MINILM (Wang et al., 2020) by only us- ing self-attention relation distillation for task- agnostic compression of pretrained Transform- ers. In particular, we define multi-head self- attention relations as scaled dot-product be- tween the pairs of query, key, and value vec- tors within each …...

Prior knowledge plays a critical role in decision-making, and humans preserve such knowledge in the form of natural language (NL). To emulate real-world decision-making, artificial agents should incorporate such generic knowledge into their decision- making framework through NL. However, since policy learning with NL-based action representation is intractable due to …...