A Neural Approach to Discourse Relation Signal Detection
- URL: http://arxiv.org/abs/2001.02380v2
- Date: Wed, 11 Mar 2020 19:56:42 GMT
- Title: A Neural Approach to Discourse Relation Signal Detection
- Abstract summary: We present a data-driven approach to signal detection using a distantly supervised neural network and develop a metric, Delta s.
The metric represents each word's positive or negative contribution to the identifiability of a relation in specific instances in context.
Our analysis examines the reliability of the metric, the places where it overlaps with and differs from human judgments, and the implications for identifying features that neural models may need.
- Score: 16.874380052348904
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Previous data-driven work investigating the types and distributions of
discourse relation signals, including discourse markers such as 'however' or
phrases such as 'as a result' has focused on the relative frequencies of signal
words within and outside text from each discourse relation. Such approaches do
not allow us to quantify the signaling strength of individual instances of a
signal on a scale (e.g. more or less discourse-relevant instances of 'and'), to
assess the distribution of ambiguity for signals, or to identify words that
hinder discourse relation identification in context ('anti-signals' or
'distractors'). In this paper we present a data-driven approach to signal
detection using a distantly supervised neural network and develop a metric,
Delta s (or 'delta-softmax'), to quantify signaling strength. Ranging between
-1 and 1 and relying on recent advances in contextualized words embeddings, the
metric represents each word's positive or negative contribution to the
identifiability of a relation in specific instances in context. Based on an
English corpus annotated for discourse relations using Rhetorical Structure
Theory and signal type annotations anchored to specific tokens, our analysis
examines the reliability of the metric, the places where it overlaps with and
differs from human judgments, and the implications for identifying features
that neural models may need in order to perform better on automatic discourse
relation classification.
Related papers
- Physics-Guided Dual Implicit Neural Representations for Source Separation [70.38762322922211]
We develop a self-supervised machine-learning approach for source separation using a dual implicit neural representation framework.<n>Our method learns directly from the raw data by minimizing a reconstruction-based loss function.<n>Our method offers a versatile framework for addressing source separation problems across diverse domains.
arXiv Detail & Related papers (2025-07-07T17:56:31Z) - Graph-Dictionary Signal Model for Sparse Representations of Multivariate Data [49.77103348208835]
We define a novel Graph-Dictionary signal model, where a finite set of graphs characterizes relationships in data distribution through a weighted sum of their Laplacians.
We propose a framework to infer the graph dictionary representation from observed data, along with a bilinear generalization of the primal-dual splitting algorithm to solve the learning problem.
We exploit graph-dictionary representations in a motor imagery decoding task on brain activity data, where we classify imagined motion better than standard methods.
arXiv Detail & Related papers (2024-11-08T17:40:43Z) - A Pilot Study on Dialogue-Level Dependency Parsing for Chinese [21.698966896156087]
We develop a high-quality human-annotated corpus, which contains 850 dialogues and 199,803 dependencies.
Considering that such tasks suffer from high annotation costs, we investigate zero-shot and few-shot scenarios.
Based on an existing syntactic treebank, we adopt a signal-based method to transform seen syntactic dependencies into unseen ones.
arXiv Detail & Related papers (2023-05-21T12:20:13Z) - Classification of Phonological Parameters in Sign Languages [0.0]
Linguistic research often breaks down signs into constituent parts to study sign languages.
We show how a single model can be used to recognise the individual phonological parameters within sign languages.
arXiv Detail & Related papers (2022-05-24T13:40:45Z) - Deep Neural Convolutive Matrix Factorization for Articulatory
Representation Decomposition [48.56414496900755]
This work uses a neural implementation of convolutive sparse matrix factorization to decompose the articulatory data into interpretable gestures and gestural scores.
Phoneme recognition experiments were additionally performed to show that gestural scores indeed code phonological information successfully.
arXiv Detail & Related papers (2022-04-01T14:25:19Z) - Resolving label uncertainty with implicit posterior models [71.62113762278963]
We propose a method for jointly inferring labels across a collection of data samples.
By implicitly assuming the existence of a generative model for which a differentiable predictor is the posterior, we derive a training objective that allows learning under weak beliefs.
arXiv Detail & Related papers (2022-02-28T18:09:44Z) - Full-Reference Speech Quality Estimation with Attentional Siamese Neural
Networks [0.0]
We present a full-reference speech quality prediction model with a deep learning approach.
The model determines a feature representation of the reference and the degraded signal through a siamese recurrent convolutional network.
The resulting features are then used to align the signals with an attention mechanism and are finally combined to estimate the overall speech quality.
arXiv Detail & Related papers (2021-05-03T12:38:25Z) - Unsupervised Sound Localization via Iterative Contrastive Learning [106.56167882750792]
We propose an iterative contrastive learning framework that requires no data annotations.
We then use the pseudo-labels to learn the correlation between the visual and audio signals sampled from the same video.
Our iterative strategy gradually encourages the localization of the sounding objects and reduces the correlation between the non-sounding regions and the reference audio.
arXiv Detail & Related papers (2021-04-01T07:48:29Z) - Learning What Makes a Difference from Counterfactual Examples and
Gradient Supervision [57.14468881854616]
We propose an auxiliary training objective that improves the generalization capabilities of neural networks.
We use pairs of minimally-different examples with different labels, a.k.a counterfactual or contrasting examples, which provide a signal indicative of the underlying causal structure of the task.
Models trained with this technique demonstrate improved performance on out-of-distribution test sets.
arXiv Detail & Related papers (2020-04-20T02:47:49Z) - Cross-modal variational inference for bijective signal-symbol
translation [11.444576186559486]
In this paper, we propose an approach for signal/symbol translation by turning this problem into a density estimation task.
We estimate this joint distribution with two different variational auto-encoders, one for each domain, whose inner representations are forced to match with an additive constraint.
In this article, we test our models on pitch, octave and dynamics symbols, which comprise a fundamental step towards music transcription and label-constrained audio generation.
arXiv Detail & Related papers (2020-02-10T15:25:48Z) - Continuous speech separation: dataset and analysis [52.10378896407332]
In natural conversations, a speech signal is continuous, containing both overlapped and overlap-free components.
This paper describes a dataset and protocols for evaluating continuous speech separation algorithms.
arXiv Detail & Related papers (2020-01-30T18:01:31Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.