Related papers: Weakly Supervised Headline Dependency Parsing

Recent work on language modelling has shifted focus from count-based models to neural models. In these works, the words in each sentence are always considered in a left-to-right order. In this paper we show how we can improve the…

Recently, channel-independent methods have achieved state-of-the-art performance in multivariate time series (MTS) forecasting. Despite reducing overfitting risks, these methods miss potential opportunities in utilizing channel dependence…

Code-switching is a phenomenon of mixing grammatical structures of two or more languages under varied social constraints. The code-switching data differ so radically from the benchmark corpora used in NLP community that the application of…

Hierarchical text classification, which aims to classify text documents into a given hierarchy, is an important task in many real-world applications. Recently, deep neural models are gaining increasing popularity for text classification due…

While the NLP community has produced numerous summarization benchmarks, none provide the rich annotations required to simultaneously address many important problems related to control and reliability. We introduce a Wikipedia-derived…

Pre-trained vision-language models learn massive data to model unified representations of images and natural languages, which can be widely applied to downstream machine learning tasks. In addition to zero-shot inference, in order to better…

Prompt learning has become a prevalent strategy for adapting vision-language foundation models to downstream tasks. As large language models (LLMs) have emerged, recent studies have explored the use of category-related descriptions as input…

Predicting emotions elicited by news headlines can be challenging as the task is largely influenced by the varying nature of people's interpretations and backgrounds. Previous works have explored classifying discrete emotions directly from…

The utility of linguistic annotation in neural machine translation seemed to had been established in past papers. The experiments were however limited to recurrent sequence-to-sequence architectures and relatively small data settings. We…

Neural NLP systems achieve high scores in the presence of sizable training dataset. Lack of such datasets leads to poor system performances in the case low-resource languages. We present two simple text augmentation techniques using…

Current state-of-the-art semantic role labeling (SRL) uses a deep neural network with no explicit linguistic features. However, prior work has shown that gold syntax trees can dramatically improve SRL decoding, suggesting the possibility of…

We propose a weakly-supervised approach that takes image-sentence pairs as input and learns to visually ground (i.e., localize) arbitrary linguistic phrases, in the form of spatial attention masks. Specifically, the model is trained with…

Attention mechanisms have improved the performance of NLP tasks while allowing models to remain explainable. Self-attention is currently widely used, however interpretability is difficult due to the numerous attention distributions. Recent…

We describe an application of an encoder-decoder recurrent neural network with LSTM units and attention to generating headlines from the text of news articles. We find that the model is quite effective at concisely paraphrasing news…

In document classification, graph-based models effectively capture document structure, overcoming sequence length limitations and enhancing contextual understanding. However, most existing graph document representations rely on heuristics,…

Story generation aims to generate a long narrative conditioned on a given input. In spite of the success of prior works with the application of pre-trained models, current neural models for Chinese stories still struggle to generate…

Finance-related news such as Bloomberg News, CNN Business and Forbes are valuable sources of real data for market screening systems. In news, an expert shares opinions beyond plain technical analyses that include context such as political,…

Content-dense news report important factual information about an event in direct, succinct manner. Information seeking applications such as information extraction, question answering and summarization normally assume all text they deal with…

This research introduces a new parsing approach, based on earlier syntactic work on context free grammar (CFG) and generalized phrase structure grammar (GPSG). The approach comprises both a new parsing algorithm and a set of syntactic rules…

Accurate syntactic representations are essential for robust generalization in natural language. Recent work has found that pre-training can teach language models to rely on hierarchical syntactic features - as opposed to incorrect linear…