Related papers: Efficient Constituency Parsing by Pointing
In this paper we first propose a new statistical parsing model, which is a generative model of lexicalised context-free grammar. We then extend the model to include a probabilistic treatment of both subcategorisation and wh-movement.…
How to make the most of multiple heterogeneous treebanks when training a monolingual dependency parser is an open question. We start by investigating previously suggested, but little evaluated, strategies for exploiting multiple treebanks…
While deep learning-based classification is generally tackled using standardized approaches, a wide variety of techniques are employed for regression. In computer vision, one particularly popular such technique is that of confidence-based…
Discriminative segmental models offer a way to incorporate flexible feature functions into speech recognition. However, their appeal has been limited by their computational requirements, due to the large number of possible segments to…
Controlling the syntactic structure of text generated by language models is valuable for applications requiring clarity, stylistic consistency, or interpretability, yet it remains a challenging task. In this paper, we argue that sampling…
While sequence-to-sequence (seq2seq) models achieve state-of-the-art performance in many natural language processing tasks, they can be too slow for real-time applications. One performance bottleneck is predicting the most likely next token…
We introduce a novel parser based on a probabilistic version of a left-corner parser. The left-corner strategy is attractive because rule probabilities can be conditioned on both top-down goals and bottom-up derivations. We develop the…
This paper describes our system (HIT-SCIR) submitted to the CoNLL 2018 shared task on Multilingual Parsing from Raw Text to Universal Dependencies. We base our submission on Stanford's winning system for the CoNLL 2017 shared task and make…
Treebanks traditionally treat punctuation marks as ordinary words, but linguists have suggested that a tree's "true" punctuation marks are not observed (Nunberg, 1990). These latent "underlying" marks serve to delimit or separate…
RST-style discourse parsing plays a vital role in many NLP tasks, revealing the underlying semantic/pragmatic structure of potentially complex and diverse documents. Despite its importance, one of the most prevailing limitations in modern…
Extractive methods have been proven effective in automatic document summarization. Previous works perform this task by identifying informative contents at sentence level. However, it is unclear whether performing extraction at sentence…
While deep reinforcement learning (RL) has been demonstrated effective in solving complex control tasks, sample efficiency remains a key challenge due to the large amounts of data required for remarkable performance. Existing research…
While the success of pre-trained language models has largely eliminated the need for high-quality static word vectors in many NLP applications, such vectors continue to play an important role in tasks where words need to be modelled in the…
BERT (Bidirectional Encoder Representations from Transformers) and related pre-trained Transformers have provided large gains across many language understanding tasks, achieving a new state-of-the-art (SOTA). BERT is pre-trained on two…
We consider the problem of conversational question answering over a large-scale knowledge base. To handle huge entity vocabulary of a large-scale knowledge base, recent neural semantic parsing based approaches usually decompose the task…
We present a novel supervised word alignment method based on cross-language span prediction. We first formalize a word alignment problem as a collection of independent predictions from a token in the source sentence to a span in the target…
This paper presents a new method for training sequence-to-sequence models for speech recognition and translation tasks. Instead of the traditional approach of training models on short segments containing only lowercase or partial…
Deciding whether a political districting plan was distorted by a hidden agenda, or whether it dilutes the voting power of some group, requires a neutral baseline for comparison. Remarkably, all nine U.S. Supreme Court justices have now…
Face segmentation is the task of densely labeling pixels on the face according to their semantics. While current methods place an emphasis on developing sophisticated architectures, use conditional random fields for smoothness, or rather…
We consider the problem of using sentence compression techniques to facilitate query-focused multi-document summarization. We present a sentence-compression-based framework for the task, and design a series of learning-based compression…