Articles

AbstractRecent works have shown that supervised models often exploit data artifacts to achieve good test scores while their performance severely degrades on samples outside their training distribution. Contrast sets (Gardneret al., 2020) quantify this phenomenon by perturbing test samples in a minimal way such that the output label is modified. …...

AbstractProbing neural models for the ability to perform downstream tasks using their activation patterns is often used to localize what parts of the network specialize in performing what tasks. However, little work addressed potential mediating factors in such comparisons. As a test-case mediating factor, we consider the prediction’s context length, …...

AbstractDue to its effectiveness and performance, the Transformer translation model has attracted wide attention, most recently in terms of probing-based approaches. Previous work focuses on using or probing source linguistic features in the encoder. To date, the way word translation evolves in Transformer layers has not yet been investigated. Naively, …...

AbstractGrounding events into a precise timeline is important for natural language understanding but has received limited attention in recent work. This problem is challenging due to the inherent ambiguity of language and the requirement for information propagation over inter-related events. This paper first formulates this problem based on a 4-tuple …...

AbstractThe tasks of Rich Semantic Parsing, such as Abstract Meaning Representation (AMR), share similar goals with Information Extraction (IE) to convert natural language texts into structured semantic representations. To take advantage of such similarity, we propose a novel AMR-guided framework for joint information extraction to discover entities, relations, and events …...

AbstractEnd-to-end relation extraction aims to identify named entities and extract relations between them. Most recent work models these two subtasks jointly, either by casting them in one structured prediction framework, or performing multi-task learning through shared representations. In this work, we present a simple pipelined approach for entity and relation …...

AbstractExisting works on information extraction (IE) have mainly solved the four main tasks separately (entity mention recognition, relation extraction, event trigger detection, and argument extraction), thus failing to benefit from inter-dependencies between tasks. This paper presents a novel deep learning model to simultaneously solve the four tasks of IE in …...

AbstractWe propose a multi-task, probabilistic approach to facilitate distantly supervised relation extraction by bringing closer the representations of sentences that contain the same Knowledge Base pairs. To achieve this, we bias the latent space of sentences via a Variational Autoencoder (VAE) that is trained jointly with a relation classifier. The …...

AbstractThe design of expressive representations of entities and relations in a knowledge graph is an important endeavor. While many of the existing approaches have primarily focused on learning from relational patterns and structural information, the intrinsic complexity of KG entities has been more or less overlooked. More concretely, we hypothesize …...

A myriad of explainability methods have been proposed in recent years, but there is little con- sensus on how to evaluate them. While auto- matic metrics allow for quick benchmarking, it isn’t clear how such metrics reflect human interaction with explanations. Human eval- uation is of paramount importance, but pre- …...

Hypernym discovery aims to identify all possi- ble hypernyms of a given term. The most re- cent hypernym discovery models exploit mul- tiple mapping functions to project a term to different semantic spaces and then aggregate these embeddings to a general representation for further classification. We refer to this model …...

Given a noun compound (NC), we address the problem of predicting the appropriate semantic label linking the constituents of the NC. This problem is called Noun Compound Interpretation (NCI). We use FrameNet as a semantic label repository. For example, given the noun compound (board approval), we pre- dict the frame …...

Sequence-to-sequence models usually transfer all encoder outputs to the decoder for genera- tion. In this work, by contrast, we hypothesize that these encoder outputs can be compressed to shorten the sequence delivered for decoding. We take Transformer as the testbed and intro- duce a layer of stochastic gates in-between the …...

Pre-trained multilingual language models (LMs) have achieved state-of-the-art results in cross-lingual transfer, but they often lead to an inequitable representation of languages due to limited capacity, skewed pre-training data, and sub-optimal vocabularies. This has prompted the creation of an ever-growing pre- trained model universe, where each model is trained on …...

The automated transcription of spoken lan- guage, and meetings, in particular, is be- coming more widespread as automatic speech recognition systems are becoming more accu- rate. This trend has significantly accelerated since the outbreak of the COVID-19 pandemic, which led to a major increase in the number of online meetings. …...

Unknown intent detection aims to identify the out-of-distribution (OOD) utterance whose in- tent has never appeared in the training set. In this paper, we propose using energy scores for this task as the energy score is theoretically aligned with the density of the input and can be derived from any …...

We propose a model that learns both the se- quential and the structural features of code for source code summarization. We adopt the abstract syntax tree (AST) and graph convolution to model the structural informa- tion and the Transformer to model the se- quential information. We convert code snip- pets …...

Recent studies on the analysis of the mul- tilingual representations focus on identifying whether there is an emergence of language- independent representations, or whether a mul- tilingual model partitions its weights among different languages. While most of such work has been conducted in a “black-box” manner, this paper aims to …...

Relation extraction (RE) is an essential topic in natural language processing and has at- tracted extensive attention. Current RE ap- proaches achieve fantastic results on common datasets, while they still struggle on practical applications. In this paper, we analyze the above performance gap, the underlying rea- son of which is …...

Despite the recent advancement in NLP re- search, cross-lingual transfer for natural lan- guage generation is relatively understudied. In this work, we transfer supervision from high resource language (HRL) to multiple low- resource languages (LRLs) for natural lan- guage generation (NLG). We consider four NLG tasks (text summarization, question gen- …...