Related papers: Efficient Constituency Parsing by Pointing

This paper presents new state-of-the-art models for three tasks, part-of-speech tagging, syntactic parsing, and semantic parsing, using the cutting-edge contextualized embedding framework known as BERT. For each task, we first replicate and…

Recent latent tree learning models can learn constituency parsing without any exposure to human-annotated tree structures. One such model is ON-LSTM (Shen et al., 2019), which is trained on language modelling and has near-state-of-the-art…

Existing approaches in disfluency detection focus on solving a token-level classification task for identifying and removing disfluencies in text. Moreover, most works focus on leveraging only contextual information captured by the linear…

Discourse parsing has long been treated as a stand-alone problem independent from constituency or dependency parsing. Most attempts at this problem are pipelined rather than end-to-end, sophisticated, and not self-contained: they assume…

Unsupervised constituency parsing focuses on identifying word sequences that form a syntactic unit (i.e., constituents) in target sentences. Linguists identify the constituent by evaluating a set of Predicate-Argument Structure (PAS)…

Naturally-occurring bracketings, such as answer fragments to natural language questions and hyperlinks on webpages, can reflect human syntactic intuition regarding phrasal boundaries. Their availability and approximate correspondence to…

Tokenization plays a critical role in language modeling, yet existing approaches such as Byte-Pair Encoding (BPE) or WordPiece operate purely on frequency statistics, ignoring the underlying semantic structure of text. This leads to…

Lexicalized parsing models are based on the assumptions that (i) constituents are organized around a lexical head (ii) bilexical statistics are crucial to solve ambiguities. In this paper, we introduce an unlexicalized transition-based…

We introduce a method for unsupervised parsing that relies on bootstrapping classifiers to identify if a node dominates a specific span in a sentence. There are two types of classifiers, an inside classifier that acts on a span, and an…

As it has been unveiled that pre-trained language models (PLMs) are to some extent capable of recognizing syntactic concepts in natural language, much effort has been made to develop a method for extracting complete (binary) parses from…

We present a novel approach to learn representations for sentence-level semantic similarity using conversational data. Our method trains an unsupervised model to predict conversational input-response pairs. The resulting sentence embeddings…

Transition-based models can be fast and accurate for constituent parsing. Compared with chart-based models, they leverage richer features by extracting history information from a parser stack, which spans over non-local constituents. On the…

We investigate the ability of transformer models to approximate the CKY algorithm, using them to directly predict a sentence's parse and thus avoid the CKY algorithm's cubic dependence on sentence length. We find that on standard…

We investigate the unsupervised constituency parsing task, which organizes words and phrases of a sentence into a hierarchical structure without using linguistically annotated data. We observe that existing unsupervised parsers capture…

Pre-trained transformer models shine in many natural language processing tasks and therefore are expected to bear the representation of the input sentence or text meaning. These sentence-level embeddings are also important in…

Punctuation restoration plays an essential role in the post-processing procedure of automatic speech recognition, but model efficiency is a key requirement for this task. To that end, we present EfficientPunct, an ensemble method with a…

This work explores constituency parsing on automatically recognized transcripts of conversational speech. The neural parser is based on a sentence encoder that leverages word vectors contextualized with prosodic features, jointly learning…

Both bottom-up and top-down strategies have been used for neural transition-based constituent parsing. The parsing strategies differ in terms of the order in which they recognize productions in the derivation tree, where bottom-up…

Syntactic natural language parsers have shown themselves to be inadequate for processing highly-ambiguous large-vocabulary text, as is evidenced by their poor performance on domains like the Wall Street Journal, and by the movement away…

Processing sentence constituency trees in binarised form is a common and popular approach in literature. However, constituency trees are non-binary by nature. The binarisation procedure changes deeply the structure, furthering constituents…