Articles

Multimodal fusion is a core problem for multi- modal sentiment analysis. Previous works usu- ally treat all three modal features equally and implicitly explore the interactions between dif- ferent modalities. In this paper, we break this kind of methods in two ways. Firstly, we ob- serve that textual modality plays …...

The adoption of natural language generation (NLG) models can leave individuals vulnera- ble to the generation of harmful information memorized by the models, such as conspiracy theories. While previous studies examine con- spiracy theories in the context of social media, they have not evaluated their presence in the new space …...

Mistranslated numbers have the potential to cause serious effects, such as financial loss or medical misinformation. In this work we develop comprehensive assessments of the ro- bustness of neural machine translation systems to numerical text via behavioural testing. We explore a variety of numerical translation capa- bilities a system is …...

Multi-hop reasoning is an effective and ex- plainable approach to predicting missing facts in Knowledge Graphs (KGs). It usually adopts the Reinforcement Learning (RL) framework and searches over the KG to find an evidential path. However, due to the large exploration space, the RL-based model struggles with the serious sparse …...

A sememe is defined as the minimum seman- tic unit in linguistics. Sememe knowledge bases (SKBs), which comprise words anno- tated with sememes, enable sememes to be ap- plied to natural language processing. So far a large body of research has showcased the unique advantages and effectiveness of SKBs in …...

There are concerns that the ability of language models (LMs) to generate high quality syn- thetic text can be misused to launch spam, dis- information, or propaganda. Therefore, the re- search community is actively working on de- veloping approaches to detect whether a given text is organic or synthetic. While …...

The paradigm of data programming, which uses weak supervision in the form of rules/labelling functions, and semi-supervised learning, which augments small amounts of labelled data with a large unlabelled dataset, have shown great promise in several text classi- fication scenarios. In this work, we argue that by not using any …...

Understanding linguistics and morphology of resource-scarce code-mixed texts remains a key challenge in text processing. Although word embedding comes in handy to support downstream tasks for low-resource languages, there are plenty of scopes in improving the quality of language representation particularly for code-mixed languages. In this paper, we propose HIT, …...

Ethical aspects of research in language tech- nologies have received much attention recently. It is a standard practice to get a study involving human subjects reviewed and approved by a professional ethics committee/board of the in- stitution. How commonly do we see mention of ethical approvals in NLP research? What …...

Event extraction (EE) aims to harvest event in- stances from plain text, where each instance is composed of a group of event arguments with specific event roles. Existing end-to-end EE re- search usually adopts the role-averaged evalu- ation that produces evaluation measures by av- eraging evaluation statistics of each event …...

Simultaneous speech-to-text translation is widely useful in many scenarios. The con- ventional cascaded approach uses a pipeline of streaming ASR followed by simultaneous MT, but suffers from error propagation and extra la- tency. To alleviate these issues, recent efforts attempt to directly translate the source speech into target text simultaneously, …...

Medical professionals review clinical narra- tives to assign medical codes as per the Inter- national Classification of Diseases (ICD) for billing and care management. This manual process is inefficient and error-prone as it in- volves a nuanced one-to-many mapping. Re- cent works on automated ICD coding learn mappings between low-dimensional …...

We present a new probing dataset named PROST: Physical Reasoning about Objects Through Space and Time. This dataset con- tains 18,736 multiple-choice questions made from 14 manually curated templates, covering 10 physical reasoning concepts. All questions are designed to probe both causal and masked language models in a zero-shot setting. …...

Script reasoning infers subsequent events from a given event chain, which involves the abil- ity to understand relations between events. A human-labeled script reasoning dataset is usu- ally of small size with limited event relations, which highlights the necessity to leverage ex- ternal eventuality knowledge graphs (KG) con- sisting of …...

Identifying relations from dialogues is more challenging than traditional sentence-level re- lation extraction (RE), since the difficulties of speaker information representation and the long-range semantic reasoning. Despite the successful efforts, existing methods do not fully consider the particularity of dialogues, making them difficult to truly understand the semantics between conversational …...

Parsing natural language questions in specific domains is crucial to a wide range of applica- tions from question-answering to dialog sys- tems. Pre-trained parsers are usually trained on corpora dominated by non-questions, and thus perform poorly on domain-specific ques- tions. Retraining parsers with domain-specific questions labeled with syntactic parse trees …...

There has been an increased interest in data generation approaches to grammatical error correction (GEC) using pseudo data. How- ever, these approaches suffer from several is- sues that make them inconvenient for real- world deployment including a demand for large amounts of training data. On the other hand, some errors …...

Social biases with respect to demographics (e.g., gender, age, race) in datasets are often encoded in the large pre-trained language mod- els trained on them. Prior works have largely focused on mitigating biases in context-free representations, with recent shift to contextual ones. While this is useful for several word and …...

Named Entity Recognition (NER) in low- resource languages has been a long-standing challenge in NLP. Recent work has shown great progress in two directions: develop- ing cross-lingual features/models to transfer knowledge to low-resource languages, and translating source-language training data into low-resource target-language training data by projecting annotations with cheap resources. …...

The ability to learn from limited data, or few- shot learning, is a desirable and often critical requirement for NLP systems. While many existing methods do poorly at learning from a handful of examples, large pretrained lan- guage models have recently been shown to be efficient few-shot learners. One approach …...