Related papers: Intonational Boundaries, Speech Repairs and Discou…
In this article, we describe some discursive segmentation methods as well as a preliminary evaluation of the segmentation quality. Although our experiment were carried for documents in French, we have developed three discursive segmentation…
We classify and re-examine some of the current approaches to improve the performance-computes trade-off of language models, including (1) non-causal models (such as masked language models), (2) extension of batch length with efficient…
Mechanistic interpretability seeks to understand the internal mechanisms of machine learning models, where localization -- identifying the important model components -- is a key step. Activation patching, also known as causal tracing or…
Most prior work in dialogue modeling has been on written conversations mostly because of existing data sets. However, written dialogues are not sufficient to fully capture the nature of spoken conversations as well as the potential speech…
In this paper, we propose an effective training strategy to ex-tract robust speaker representations from a speech signal. Oneof the key challenges in speaker recognition tasks is to learnlatent representations or embeddings containing…
A Prompt-based Text-To-Speech model allows a user to control different aspects of speech, such as speaking rate and perceived gender, through natural language instruction. Although user-friendly, such approaches are on one hand constrained:…
The usual way to interpret language models (LMs) is to test their performance on different benchmarks and subsequently infer their internal processes. In this paper, we present an alternative approach, concentrating on the quality of LM…
Multilingual language models have recently gained attention as a promising solution for representing multiple languages in a single model. In this paper, we propose new criteria to evaluate the quality of lexical representation and…
Many of the kinds of language model used in speech understanding suffer from imperfect modeling of intra-sentential contextual influences. I argue that this problem can be addressed by clustering the sentences in a training corpus…
We introduce a linguistically enhanced combination of pre-training methods for transformers. The pre-training objectives include POS-tagging, synset prediction based on semantic knowledge graphs, and parent prediction based on dependency…
Discourse coherence plays an important role in the translation of one text. However, the previous reported models most focus on improving performance over individual sentence while ignoring cross-sentence links and dependencies, which…
Multi-talker automatic speech recognition (ASR) has been studied to generate transcriptions of natural conversation including overlapping speech of multiple speakers. Due to the difficulty in acquiring real conversation data with…
We present a method of finding and analyzing shifts in grammatical relations found in diachronic corpora. Inspired by the econometric technique of measuring return and volatility instead of relative frequencies, we propose them as a way to…
A multi-turn dialogue is composed of multiple utterances from two or more different speaker roles. Thus utterance- and speaker-aware clues are supposed to be well captured in models. However, in the existing retrieval-based multi-turn…
We train one multilingual model for dependency parsing and use it to parse sentences in several languages. The parsing model uses (i) multilingual word clusters and embeddings; (ii) token-level language information; and (iii)…
We present an empirical investigation of various ways to automatically identify phrases in a tagged corpus that are useful for dialogue act tagging. We found that a new method (which measures a phrase's deviation from an…
Language models typically tokenize text into subwords, using a deterministic, hand-engineered heuristic of combining characters into longer surface-level strings such as 'ing' or whole words. Recent literature has repeatedly shown the…
Spoken language understanding system is traditionally designed as a pipeline of a number of components. First, the audio signal is processed by an automatic speech recognizer for transcription or n-best hypotheses. With the recognition…
This paper explores the challenges posed by nominal adjectives (NAs) in natural language processing (NLP) tasks, particularly in part-of-speech (POS) tagging. We propose treating NAs as a distinct POS tag, "JN," and investigate its impact…
A new language model for speech recognition inspired by linguistic analysis is presented. The model develops hidden hierarchical structure incrementally and uses it to extract meaningful information from the word history - thus enabling the…