1 |
ViQuAE, a Dataset for Knowledge-based Visual Question Answering about Named Entities
|
|
|
|
In: ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR ’22) ; https://hal-universite-paris-saclay.archives-ouvertes.fr/hal-03650618 ; 2022 (2022)
|
|
BASE
|
|
Show details
|
|
2 |
FedQAS: Privacy-Aware Machine Reading Comprehension with Federated Learning
|
|
|
|
In: Applied Sciences; Volume 12; Issue 6; Pages: 3130 (2022)
|
|
BASE
|
|
Show details
|
|
3 |
English machine reading comprehension: new approaches to answering multiple-choice questions
|
|
Dzendzik, Daria. - : Dublin City University. School of Computing, 2021. : Dublin City University. ADAPT, 2021
|
|
In: Dzendzik, Daria (2021) English machine reading comprehension: new approaches to answering multiple-choice questions. PhD thesis, Dublin City University. (2021)
|
|
BASE
|
|
Show details
|
|
4 |
Unsupervised Morphological Segmentation and Part-of-Speech Tagging for Low-Resource Scenarios
|
|
|
|
Abstract:
With the high cost of manually labeling data and the increasing interest in low-resource languages, for which human annotators might not be even available, unsupervised approaches have become essential for processing a typologically diverse set of languages, whether high-resource or low-resource. In this work, we propose new fully unsupervised approaches for two tasks in morphology: unsupervised morphological segmentation and unsupervised cross-lingual part-of-speech (POS) tagging, which have been two essential subtasks for several downstream NLP applications, such as machine translation, speech recognition, information extraction and question answering. We propose a new unsupervised morphological-segmentation approach that utilizes Adaptor Grammars (AGs), nonparametric Bayesian models that generalize probabilistic context-free grammars (PCFGs), where a PCFG models word structure in the task of morphological segmentation. We implement the approach as a publicly available morphological-segmentation framework, MorphAGram, that enables unsupervised morphological segmentation through the use of several proposed language-independent grammars. In addition, the framework allows for the use of scholar knowledge, when available, in the form of affixes that can be seeded into the grammars. The framework handles the cases when the scholar-seeded knowledge is either generated from language resources, possibly by someone who does not know the language, as weak linguistic priors, or generated by an expert in the underlying language as strong linguistic priors. Another form of linguistic priors is the design of a grammar that models language-dependent specifications. We also propose a fully unsupervised learning setting that approximates the effect of scholar-seeded knowledge through self-training. Moreover, since there is no single grammar that works best across all languages, we propose an approach that picks a nearly optimal configuration (a learning setting and a grammar) for an unseen language, a language that is not part of the development. Finally, we examine multilingual learning for unsupervised morphological segmentation in low-resource setups. For unsupervised POS tagging, two cross-lingual approaches have been widely adapted: 1) annotation projection, where POS annotations are projected across an aligned parallel text from a source language for which a POS tagger is accessible to the target one prior to training a POS model; and 2) zero-shot model transfer, where a model of a source language is directly applied on texts in the target language. We propose an end-to-end architecture for unsupervised cross-lingual POS tagging via annotation projection in truly low-resource scenarios that do not assume access to parallel corpora that are large in size or represent a specific domain. We integrate and expand the best practices in alignment and projection and design a rich neural architecture that exploits non-contextualized and transformer-based contextualized word embeddings, affix embeddings and word-cluster embeddings. Additionally, since parallel data might be available between the target language and multiple source ones, as in the case of the Bible, we propose different approaches for learning from multiple sources. Finally, we combine our work on unsupervised morphological segmentation and unsupervised cross-lingual POS tagging by conducting unsupervised stem-based cross-lingual POS tagging via annotation projection, which relies on the stem as the core unit of abstraction for alignment and projection, which is beneficial to low-resource morphologically complex languages. We also examine morpheme-based alignment and projection, the use of linguistic priors towards better POS models and the use of segmentation information as learning features in the neural architecture. We conduct comprehensive evaluation and analysis to assess the performance of our approaches of unsupervised morphological segmentation and unsupervised POS tagging and show that they achieve the state-of-the-art performance for the two morphology tasks when evaluated on a large set of languages of different typologies: analytic, fusional, agglutinative and synthetic/polysynthetic.
|
|
Keyword:
Automatic speech recognition--Computer programs; Computer science; Machine translating; Question-answering systems; Speech processing systems--Computer programs
|
|
URL: https://doi.org/10.7916/d8-jd2d-9p51
|
|
BASE
|
|
Hide details
|
|
5 |
Geographic Question Answering with Spatially-Explicit Machine Learning Models
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Neural Question Answering Models with Broader Knowledge Scope and Deeper Reasoning Power
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Exploiting multimodality and structure in world representations ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Enhancing multiple-choice question answering with causal knowledge
|
|
|
|
BASE
|
|
Show details
|
|
10 |
ViquiQuAD: an extractive QA dataset from Catalan Wikipedia ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
ViquiQuAD: an extractive QA dataset from Catalan Wikipedia ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
VilaQuAD: an extractive QA dataset from Catalan newswire ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
VilaQuAD: an extractive QA dataset from Catalan newswire ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
CRAFT: A Benchmark for Causal Reasoning About Forces and inTeractions ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
CRAFT: A Benchmark for Causal Reasoning About Forces and inTeractions ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Unsupervised Morphological Segmentation and Part-of-Speech Tagging for Low-Resource Scenarios ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
WebSRC: A Dataset for Web-Based Structural Reading Comprehension ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Semantic Categorization of Social Knowledge for Commonsense Question Answering ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
ESTER: A Machine Reading Comprehension Dataset for Reasoning about Event Semantic Relations ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|