Taiwan

This paper focuses on the generation of natural language questions based on SPARQL queries, with an emphasis on conversational use cases (follow-up question-answering). It studies what can be achieved so far based on current deep learning models (namely pretrained T5 and BART models). To do so, 4 knowledge-based QA corpora have been homogenized for the task and a new challenge set is introduced. A first series of experiments analyzes the impact of different training setups, while a second series seeks to understand what is still difficult for these models. The results from automatic metrics and human evaluation show that simple questions and frequent templates of SPARQL queries are usually well processed whereas complex questions and conversational dimensions (coreferences and ellipses) are still difficult to handle. The experimental material is publicly available on https://github.com/Orange-OpenSource/sparql-to-text .

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-main.11/)

IJCNLP-AACL 2022

SPARQL-to-Text Question Generation for Knowledge-Based Conversational Applications

sparql

conversational question-answering

natural language generation

knowledge graphs

The purpose of the AAAI conference is to promote research in artificial intelligence (AI) and scientific exchange among AI researchers, practitioners, scientists, and engineers in affiliated disciplines. 

AAAI 2022

poster

The AACL, Asia-Pacific Chapter of the Association for Computational Linguistics, and the AFNLP, Asian Federation of Natural Language Processing, invite you to participate in the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (AACL) and the 10th International Joint Conference on Natural Language Processing (IJCNLP). 
<br>
<br>

A registration is required to access this event. Access to the event site will be granted to all registered attendees on **November 16th**. If you have not already done so, please register using the link below:
<br>
<br>https://conference.iis.sinica.edu.tw/servlet/Register?ConferenceID=411

Registration Is Required

The AACL, Asia-Pacific Chapter of the Association for Computational Linguistics, and the AFNLP, Asian Federation of Natural Language Processing, invite you to participate in the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (AACL) and the 10th International Joint Conference on Natural Language Processing (IJCNLP). 

Knowledge graph embedding (KGE) has been well-studied in general domains, but has not been examined for food computing. To fill this gap, we perform knowledge representation learning over a food knowledge graph (KG). We employ a pre-trained language model to encode entities and relations, thus emphasizing- ing contextual information in food KGs. The model is trained on two tasks – predicting a masked entity from a given triple from the KG and predicting the plausibility of a triple. Analysis of food substitutions helps in dietary choices for enabling healthier eating behaviors. Previous work in food substitutions mainly focuses on semantic similarity while ignoring the context. It is also hard to evaluate the substitutions due to the lack of an adequate validation set, and further, the evaluation is sub- jective based on perceived purpose. To tackle this problem, we propose a collection of adversarial sample generation strategies for different food substitutions over our learnt KGE. We pro- pose multiple strategies to generate high-quality context-aware recipe and ingredient substitutions and also provide generalized ingredient substitutions to meet different user needs. The effectiveness and efficiency of the proposed knowledge graph learning method and the following attack strategies are verified by extensive evaluations on a large-scale food KG.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-main.50/)

Food Knowledge Representation Learning with Adversarial Substitution

In recent years, knowledge graphs (KGs) have attracted a surge of interest from both academia and industry. As a representation of semantic relations between entities, KGs have proven to be particularly relevant for natural language processing (NLP). Despite the increasing amount of research work in this area, a comprehensive study that categorizes established topics and reviews emerging research streams remains absent to this day. To provide an overview of the research landscape of KGs in NLP, we analyzed 507 papers in a multifaceted survey of tasks, research types, and contributions.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-main.46/)

A Decade of Knowledge Graphs in Natural Language Processing: A Survey

Keywords or keyphrases are often used to highlight a document's domains or main topics. Unsupervised keyphrase extraction (UKE) has always been highly anticipated because no labeled data is needed to train a model. This paper proposes an augmented graph-based unsupervised model to identify keyphrases from a document by integrating graph and deep learning methods. The proposed model utilizes mutual attention extracted from the pre-trained BERT model to build the candidate graph and augments the graph with global and local context nodes to improve the performance. The proposed model is evaluated on four publicly available datasets against thirteen UKE baselines. The results show that the proposed model is an effective and robust UKE model for long and short documents. Our source code is available on GitHub.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-main.19/)

AGRank: Augmented Graph-based Unsupervised Keyphrase Extraction

Reasoning with preconditions such as “glass can be used for drinking water unless the glass is shattered” remains an open problem for language models. The main challenge lies in the scarcity of preconditions data and the model’s lack of support for such reasoning. We present PInKS, Preconditioned Commonsense Inference with WeaK Supervision, an improved model for reasoning with preconditions through minimum supervision. We show, both empirically and theoretically, that PInKS improves the results on benchmarks focused on reasoning with the preconditions of commonsense knowledge (up to 40% Macro-F1 scores). We further investigate PInKS through PAC-Bayesian informativeness analysis, precision measures, and ablation study.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-main.26/)

PInKS: Preconditioned Commonsense Inference with Minimal Supervision

In this research, we propose CNN based CoCNN+ model can beat transformer models in Bengali and Hindi language modeling - two of the most popular languages in the world. These languages have high inflection, flexible word order, and a lot of compound characters making them morphologically rich. Base CoCNN model has two components – 1D CNN based vocabulary learner works at word level, while terminal coordinator works at document level. We analyze CNN, LSTM and Transformer based models for Bengali language modeling using perplexity score. CNNs do a better job than LSTMs because of the flexible word order in Bengali. CoCNN has on par performance with pretrained BERT. We extend the base CoCNN to CoCNN+ by incorporating residual connection in the shallow layers of vocabulary learner and by introducing parallel branches of different convolution widths in the terminal coordinator. These modifications help CoCNN beat pretrained BERT for Bengali and Hindi next word prediction, text classification and sentiment analysis tasks.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-main.4/)

CNN for Modeling Sanskrit Originated Bengali and Hindi Language

Word embeddings and pre-trained language models have become essential technical elements in natural language processing. While the general practice is to use or fine-tune publicly available models, there are significant advantages in creating or pre-training unique models that match the domain. The performance of the models degrades as language changes or evolves continuously (semantic shift), but the high cost of model building inhibits regular re-training, especially for the language models. This study designs a methodology for observing time-series performance degradation of word embeddings and pre-trained language models using semantic shift in a corpus. We define an efficiently computable metric named Semantic Shift Stability based on the degree of semantic shift. In the experiments, we create models that vary by time series and reveal the performance degradation in two datasets, Japanese and English. Several case studies demonstrate that Semantic Shift Stability supports decision-making as to whether a model should be re-trained. The source code is available at https://github.com/Nikkei/semantic-shift-stability.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-main.17/)

Semantic Shift Stability: Efficient Way to Detect Performance Degradation of Word Embeddings and Pre-trained Language Models

As we begin to see low-powered computing paradigms (Neuromorphic Computing, Spiking Neural Networks, etc.) becoming more popular, learning binary word embeddings has become increasingly important for supporting NLP applications at the edge. Existing binary word embeddings are mostly derived from pretrained real-valued embeddings through different simple transformations, which often break the semantic consistency and the so-called "arithmetic'' properties learned by the original, real-valued embeddings. This paper aims to address this limitation by introducing a new approach to learn binary embeddings from scratch, preserving the semantic relationships between words as well as the arithmetic properties of the embeddings themselves. To achieve this, we propose a novel genetic algorithm to learn the relationships between words from existing word analogy data-sets, carefully making sure that the arithmetic properties of the relationships are preserved. Evaluating our generated 16, 32, and 64-bit binary word embeddings on Mikolov's word analogy task shows that more than 95% of the time, the best fit for the analogy is ranked in the top 5 most similar words in terms of cosine similarity.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-main.52/)

Analogy-Guided Evolutionary Pretraining of Binary Word Embeddings

In this work, we introduced a novel inference problem that calls for research towards unifying the Representations of Knowledge Graphs and Expert Rules for Machine Learning and Reasoning. Our work is motivated by the following overarching question: With a knowledge graph and a set of if-then rules, can we reason about the conclusions given a set of observations w/ or w/o any labeled data? Based on our work, the short answer to this question is, yes, we can. And we show that the proposed framework has great potential in performing complex inference tasks through empirical study.

Note that our work should be viewed as a proof of concept of the general idea. Please check out the paper for more details. Thank you!

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-main.20/)

Towards Integrating Knowledge Graph and Expert Rules for Machine Learning and Reasoning

We aim to develop methods for understanding how multimedia news exposure can affect people’s emotional responses, and we especially focus on news content related to gun violence, a very important yet polarizing issue in the U.S. We created the dataset NEmo+ by significantly extending the U.S. gun violence news-to-emotions dataset, BU-NEmo, from 320 to 1,297 news headline and lead image pairings and collecting 38,910 annotations in a large crowdsourcing experiment. In curating the NEmo+ dataset, we developed methods to identify news items that will trigger similar versus divergent emotional responses. For news items that trigger similar emotional responses, we compiled them into the NEmo+-Consensus dataset. We benchmark models on this dataset that predict a person's dominant emotional response toward the target news item (single-label prediction). On the full NEmo+ dataset, containing news items that would lead to both differing and similar emotional responses, we also benchmark models for the novel task of predicting the distribution of evoked emotional responses in humans when presented with multi-modal news content. Our single-label and multi-label prediction models outperform baselines by large margins across several metrics.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-main.29/)

Prediction of People's Emotional Response towards Multi-modal News

Current language models achieve low perplexity but their resulting generations still suffer from toxic responses, repetitiveness, and contradictions. The standard language modeling setup fails to address these issues. In this paper, we introduce a new architecture, Director, that consists of a unified generator-classifier with both a language modeling and a classification head for each output token. Training is conducted jointly using both standard language modeling data, and data labeled with desirable and undesirable sequences. Experiments in several settings show that the model has competitive training and decoding speed compared to standard language models while yielding superior results, avoiding undesirable behaviors while maintaining generation quality. It also outperforms existing model-guiding approaches in terms of both accuracy and efficiency.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-main.39/)

Downloads

Next from IJCNLP-AACL 2022

Food Knowledge Representation Learning with Adversarial Substitution

Similar lecture

BigCQ: Generating a Synthetic Set of Competency Questions Formalized into SPARQL-OWL (Student Abstract)