Deep Learning Inside Out (DeeLIO): The Workshop on Knowledge Extraction and Integration for Deep Learning Architectures (2022)


up

pdf (full)
bib (full)
Proceedings of Deep Learning Inside Out (DeeLIO 2022): The 3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures

pdf bib
Proceedings of Deep Learning Inside Out (DeeLIO 2022): The 3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures
Eneko Agirre | Marianna Apidianaki | Ivan Vulić

pdf bib
Cross-lingual Semantic Role Labelling with the ValPaL Database Knowledge
Chinmay Choudhary | Colm O’Riordan

Cross-lingual Transfer Learning typically involves training a model on a high-resource sourcelanguage and applying it to a low-resource tar-get language. In this work we introduce a lexi-cal database calledValency Patterns Leipzig(ValPal)which provides the argument patterninformation about various verb-forms in mul-tiple languages including low-resource langua-ges. We also provide a framework to integratethe ValPal database knowledge into the state-of-the-art LSTM based model for cross-lingualsemantic role labelling. Experimental resultsshow that integrating such knowledge resultedin am improvement in performance of the mo-del on all the target languages on which it isevaluated.

pdf bib
How Do Transformer-Architecture Models Address Polysemy of Korean Adverbial Postpositions?
Seongmin Mun | Guillaume Desagulier

Postpositions, which are characterized as multiple form-function associations and thus polysemous, pose a challenge to automatic identification of their usage. Several studies have used contextualized word-embedding models to reveal the functions of Korean postpositions. Despite the superior classification performance of previous studies, the particular reason how these models resolve the polysemy of Korean postpositions is not enough clear. To add more interpretation, for this reason, we devised a classification model by employing two transformer-architecture models—BERT and GPT-2—and introduces a computational simulation that interactively demonstrates how these transformer-architecture models simulate human interpretation of word-level polysemy involving Korean adverbial postpositions -ey, -eyse, and -(u)lo. Results reveal that (i) the BERT model performs better than the GPT-2 model to classify the intended function of postpositions, (ii) there is an inverse relationship between the classification accuracy and the number of functions that each postposition manifests, (iii) model performance is affected by the corpus size of each function, (iv) the models’ performance gradually improves as the epoch proceeds, and (vi) the models are affected by the scarcity of input and/or semantic closeness between the items.

pdf
Query Generation with External Knowledge for Dense Retrieval
Sukmin Cho | Soyeong Jeong | Wonsuk Yang | Jong Park

Dense retrieval aims at searching for the most relevant documents to the given query by encoding texts in the embedding space, requiring a large amount of query-document pairs to train. Since manually constructing such training data is challenging, recent work has proposed to generate synthetic queries from documents and use them to train a dense retriever. However, compared to the manually composed queries, synthetic queries do not generally ask for implicit information, therefore leading to a degraded retrieval performance. In this work, we propose Query Generation with External Knowledge (QGEK), a novel method for generating queries with external information related to the corresponding document. Specifically, we convert a query into a triplet-based template form to accommodate external information and transmit it to a pre-trained language model (PLM). We validate QGEK on both in-domain and out-domain dense retrieval settings. The dense retriever with the queries requiring implicit information is found to make good performance improvement. Also, such queries are similar to manually composed queries, confirmed by both human evaluation and unique & non-unique words distribution.

pdf
Uncovering Values: Detecting Latent Moral Content from Natural Language with Explainable and Non-Trained Methods
Luigi Asprino | Luana Bulla | Stefano De Giorgis | Aldo Gangemi | Ludovica Marinucci | Misael Mongiovi

Moral values as commonsense norms shape our everyday individual and community behavior. The possibility to extract moral attitude rapidly from natural language is an appealing perspective that would enable a deeper understanding of social interaction dynamics and the individual cognitive and behavioral dimension. In this work we focus on detecting moral content from natural language and we test our methods on a corpus of tweets previously labeled as containing moral values or violations, according to Moral Foundation Theory. We develop and compare two different approaches: (i) a frame-based symbolic value detector based on knowledge graphs and (ii) a zero-shot machine learning model fine-tuned on a task of Natural Language Inference (NLI) and a task of emotion detection. The final outcome from our work consists in two approaches meant to perform without the need for prior training process on a moral value detection task.

pdf
Jointly Identifying and Fixing Inconsistent Readings from Information Extraction Systems
Ankur Padia | Francis Ferraro | Tim Finin

Moral values as commonsense norms shape our everyday individual and community behavior. The possibility to extract moral attitude rapidly from natural language is an appealing perspective that would enable a deeper understanding of social interaction dynamics and the individual cognitive and behavioral dimension. In this work we focus on detecting moral content from natural language and we test our methods on a corpus of tweets previously labeled as containing moral values or violations, according to Moral Foundation Theory. We develop and compare two different approaches: (i) a frame-based symbolic value detector based on knowledge graphs and (ii) a zero-shot machine learning model fine-tuned on a task of Natural Language Inference (NLI) and a task of emotion detection. The final outcome from our work consists in two approaches meant to perform without the need for prior training process on a moral value detection task.

pdf
KIQA: Knowledge-Infused Question Answering Model for Financial Table-Text Data
Rungsiman Nararatwong | Natthawut Kertkeidkachorn | Ryutaro Ichise

While entity retrieval models continue to advance their capabilities, our understanding of their wide-ranging applications is limited, especially in domain-specific settings. We highlighted this issue by using recent general-domain entity-linking models, LUKE and GENRE, to inject external knowledge into a question-answering (QA) model for a financial QA task with a hybrid tabular-textual dataset. We found that both models improved the baseline model by 1.57% overall and 8.86% on textual data. Nonetheless, the challenge remains as they still struggle to handle tabular inputs. We subsequently conducted a comprehensive attention-weight analysis, revealing how LUKE utilizes external knowledge supplied by GENRE. The analysis also elaborates how the injection of symbolic knowledge can be helpful and what needs further improvement, paving the way for future research on this challenging QA task and advancing our understanding of how a language model incorporates external knowledge.

pdf
Trans-KBLSTM: An External Knowledge Enhanced Transformer BiLSTM Model for Tabular Reasoning
Yerram Varun | Aayush Sharma | Vivek Gupta

Natural language inference on tabular data is a challenging task. Existing approaches lack the world and common sense knowledge required to perform at a human level. While massive amounts of KG data exist, approaches to integrate them with deep learning models to enhance tabular reasoning are uncommon. In this paper, we investigate a new approach using BiLSTMs to incorporate knowledge effectively into language models. Through extensive analysis, we show that our proposed architecture, Trans-KBLSTM improves the benchmark performance on InfoTabS, a tabular NLI dataset.

pdf
Fast Few-shot Debugging for NLU Test Suites
Christopher Malon | Kai Li | Erik Kruus

We study few-shot debugging of transformer based natural language understanding models, using recently popularized test suites to not just diagnose but correct a problem. Given a few debugging examples of a certain phenomenon, and a held-out test set of the same phenomenon, we aim to maximize accuracy on the phenomenon at a minimal cost of accuracy on the original test set. We examine several methods that are faster than full epoch retraining. We introduce a new fast method, which samples a few in-danger examples from the original training set. Compared to fast methods using parameter distance constraints or Kullback-Leibler divergence, we achieve superior original accuracy for comparable debugging accuracy.

pdf
On Masked Language Models for Contextual Link Prediction
Angus Brayne | Maciej Wiatrak | Dane Corneil

In the real world, many relational facts require context; for instance, a politician holds a given elected position only for a particular timespan. This context (the timespan) is typically ignored in knowledge graph link prediction tasks, or is leveraged by models designed specifically to make use of it (i.e. n-ary link prediction models). Here, we show that the task of n-ary link prediction is easily performed using language models, applied with a basic method for constructing cloze-style query sentences. We introduce a pre-training methodology based around an auxiliary entity-linked corpus that outperforms other popular pre-trained models like BERT, even with a smaller model. This methodology also enables n-ary link prediction without access to any n-ary training set, which can be invaluable in circumstances where expensive and time-consuming curation of n-ary knowledge graphs is not feasible. We achieve state-of-the-art performance on the primary n-ary link prediction dataset WD50K and on WikiPeople facts that include literals - typically ignored by knowledge graph embedding methods.

pdf
What Makes Good In-Context Examples for GPT-3?
Jiachang Liu | Dinghan Shen | Yizhe Zhang | Bill Dolan | Lawrence Carin | Weizhu Chen

GPT-3 has attracted lots of attention due to its superior performance across a wide range of NLP tasks, especially with its in-context learning abilities. Despite its success, we found that the empirical results of GPT-3 depend heavily on the choice of in-context examples. In this work, we investigate whether there are more effective strategies for judiciously selecting in-context examples (relative to random sampling) that better leverage GPT-3’s in-context learning capabilities. Inspired by the recent success of leveraging a retrieval module to augment neural networks, we propose to retrieve examples that are semantically-similar to a test query sample to formulate its corresponding prompt. Intuitively, the examples selected with such a strategy may serve as more informative inputs to unleash GPT-3’s power of text generation. We evaluate the proposed approach on several natural language understanding and generation benchmarks, where the retrieval-based prompt selection approach consistently outperforms the random selection baseline. Moreover, it is observed that the sentence encoders fine-tuned on task-related datasets yield even more helpful retrieval results. Notably, significant gains are observed on tasks such as table-to-text generation (44.3% on the ToTTo dataset) and open-domain question answering (45.5% on the NQ dataset).