Related papers: Improving Zero-shot Sentence Decontextualisation w…
Long-context large language models remain computationally expensive to run and often fail to reliably process very long inputs, which makes context compression an important component of many systems. Existing compression approaches…
Text semantic matching is a fundamental task that has been widely used in various scenarios, such as community question answering, information retrieval, and recommendation. Most state-of-the-art matching models, e.g., BERT, directly…
Event extraction (EE) is the task of identifying interested event mentions from text. Conventional efforts mainly focus on the supervised setting. However, these supervised models cannot generalize to event types out of the pre-defined…
Traditional approaches to extractive summarization rely heavily on human-engineered features. In this work we propose a data-driven approach based on neural networks and continuous sentence features. We develop a general framework for…
When searching the web, it is often possible that there are too many results available for ambiguous queries. Text snippets, extracted from the retrieved pages, are an indicator of the pages' usefulness to the query intention and can be…
Building effective text generation systems requires three critical components: content selection, text planning, and surface realization, and traditionally they are tackled as separate problems. Recent all-in-one style neural generation…
When writing a summary, humans tend to choose content from one or two sentences and merge them into a single summary sentence. However, the mechanisms behind the selection of one or multiple source sentences remain poorly understood.…
Zero-shot Learners are models capable of predicting unseen classes. In this work, we propose a Zero-shot Learning approach for text categorization. Our method involves training model on a large corpus of sentences to learn the relationship…
Sentence ordering is a general and critical task for natural language generation applications. Previous works have focused on improving its performance in an external, downstream task, such as multi-document summarization. Given its…
Understanding inferences and answering questions from text requires more than merely recovering surface arguments, adjuncts, or strings associated with the query terms. As humans, we interpret sentences as contextualized components of a…
Citation texts are sometimes not very informative or in some cases inaccurate by themselves; they need the appropriate context from the referenced paper to reflect its exact contributions. To address this problem, we propose an unsupervised…
Selective rationalization aims to produce decisions along with rationales (e.g., text highlights or word alignments between two sentences). Commonly, rationales are modeled as stochastic binary masks, requiring sampling-based gradient…
An important task in NLP applications such as sentence simplification is the ability to take a long, complex sentence and split it into shorter sentences, rephrasing as necessary. We introduce a novel dataset and a new model for this `split…
Automated multi-document extractive text summarization is a widely studied research problem in the field of natural language understanding. Such extractive mechanisms compute in some form the worthiness of a sentence to be included into the…
News Image Captioning requires describing an image by leveraging additional context from a news article. Previous works only coarsely leverage the article to extract the necessary context, which makes it challenging for models to identify…
Automatic sentence summarization produces a shorter version of a sentence, while preserving its most important information. A good summary is characterized by language fluency and high information overlap with the source sentence. We model…
Document-level neural machine translation has yielded attractive improvements. However, majority of existing methods roughly use all context sentences in a fixed scope. They neglect the fact that different source sentences need different…
Text summarization has been one of the most challenging areas of research in NLP. Much effort has been made to overcome this challenge by using either the abstractive or extractive methods. Extractive methods are more popular, due to their…
The recent advances in transfer learning techniques and pre-training of large contextualized encoders foster innovation in real-life applications, including dialog assistants. Practical needs of intent recognition require effective data…
It is expensive and difficult to obtain the large number of sentence-level intent and token-level slot label annotations required to train neural network (NN)-based Natural Language Understanding (NLU) components of task-oriented dialog…