Question Answering

Question answering (NLQA) systems which retrieve a textual fragment from a document collection that represents the answer to a question are an active field of research. But evaluations currently involve a large amount of manual effort. We propose a new evaluation scheme that uses the insertion of answers from Frequently Asked Questions collections (FAQs) to measure the ability of a system to retrieve it from the corresponding question. We describe how the usefulness of the approach can be assessed and discuss advantages and problems.

Current methods of coding recall, summarization, talk-aloud, and question-answering data are inherently unreliable and not effectively documented. If the process of coding protocol data could even be partially automated, this would be an im- portant scientific advance in the field of text comprehension. Twenty-four human subjects read and recalled each of four short texts. Half of the human recall data

One of the most accurate methods in Question Answering (QA) uses off-line information extraction to find answers for frequently asked questions. It requires automatic extraction from text of all relation instances for relations that users frequently ask for. In this chapter, two methods are presented for learning relation instances for relations relevant in a closed and open domain (medical) QA system. Both methods try to learn automatic dependency paths that typically connect two arguments of a given relation. The first (lightly supervised) method starts from a seed list of argument instances, and extracts dependency paths from all sentences in which a seed pair occurs. This method works well for large text collections and for seeds which are easily identified, such as named entities, and is well-suited for open domain QA. A second experiment concentrates on medical relation extraction for the question answering module of the IMIX system. The IMIX corpus is relatively small and relation instances may contain complex noun phrases that do not occur frequently in the exact same form in the corpus. In this case, learning from annotated data is necessary. Dependency patterns enriched with semantic concept labels are shown to give accurate results for relations that are relevant for a medical QA system. Both methods improve the performance of the Dutch QA system Joost.

A most prominent phenomenon of natural lan-guages is variability-stating the same meaning in various ways. Robust language processing applica-tions-like Information Retrieval (IR), Question Answering (QA), Information Extraction (IE), text summarization and machine translation-must recognize the different forms in which their inputs and requested outputs might be expressed. Today, inferences about language variability are often per-formed by practical systems at a

This paper considers a surface-based question answering system for an open- domain solution. It analyzes the current progress that has been done in this area so far, while as well describes a methodology of answering questions by using information retrieved from very large collection of text. The solution proposed is based on indexing techniques and surface-based natural language processing that identify paragraphs from which an answer can be extracted. Although this approach would not solve all the problems associated with this task the objective is to provide a solution that is feasible, achieves reasonable accuracy and can return an answer in an acceptable time limit. Various techniques are discussed including question analysis, question reformulation, term extraction, answer extraction and other methods for answer pinpointing. Besides this further research in question answering is identified, especially in the area of handling answers that require reasoning.

The proper interpretation of prepositions is an important issue for automatic natu- ral language understanding. We present an approach towards PP interpretation as part of a natural language understanding system which has been successfully em- ployed in various NLP tasks for informa- tion retrieval and question answering. Our approach is based on the so-called Multi- Net paradigm, a knowledge representation

Natural Language Processing is a programmed approach to analyze text that is based on both a
set of theories and a set of technologies. This forum aims to bring together researchers who have
designed and build software that will analyze, understand, and generate languages that humans
use naturally to address computers.

В статье обсуждается проблема преобразования классификации речевых актов, заимствованной из философии, в типологическую категорию. Трудность такого преобразования лежит в широкой вариативности формы выражения иллокутивной силы. Несмотря на то, что с основными речевыми актами традиционно ассоциируют определенные формальные признаки (ср. интонационный контур для вопроса), это не позволяет учесть более тонкой классификации (например, противопоставить комплимент сообщению о факте), а главное — полностью исключает из рассмотрения косвенные речевые акты, в природе которых лежит непрямое соответствие формы смыслу сообщения. Для преодоления этого обстоятельства в качестве маркеров категории предлагается рассматривать языковые единицы за пределами речевого акта, а именно специальный класс идиоматичных ответных реплик (ср.: А как же!, Не скажи!, Еще чего!), называемых дискурсивными формулами. Для исследования этого класса авторы опираются на со- ставленный для русского языка список из более 700 формул. Корпусный анализ их употребления показывает, что использование дискурсивных формул во многом зависит от иллокутивной силы высказывания, на которое они реагируют. Сравнение сочетаемости дискурсивных формул в разных языках дает возможность выделить релевантные прагматические противопоставления среди контекстных высказываний. Представленный в статье опыт такого исследования на небольшом фрагменте стимульных речевых актов для русских и английских формул запрета и отказа показывает, что данный материал имеет потенциал для проверки, уточнения и дополнения общепринятой классификации с лингвистического ракурса.

Natural Language Processing is a programmed approach to analyze text that is based on both a set of theories and a set of technologies. This forum aims to bring together researchers who have designed and build software that will analyze, understand, and generate languages that humans use naturally to address computers.

3rd International Conference on NLP & Information Retrieval (NLPI 2022) will provide an excellent international forum for sharing knowledge and results in theory, methodology and applications of Natural Language Computing and Information Retrieval.

Current text-based question answering (QA) systems usually contain a named entity recogniser (NER) as a core component. Named entity recognition has traditionally been developed as a component for information extraction systems, and current techniques are focused on this end use. However, no formal assessment has been done on the characteristics of a NER within the task of question answering. In this paper we present a NER that aims at higher recall by allowing multiple entity labels to strings. The NER is ...

Résumé In this paper, we present the LIMSI question-answering systems on speech transcripts which participated to the QAst 2008 evaluation. These systems are based on a complete and multi- level analysis of both queries and documents. These systems use an automatically generated research descriptor. A score based on those descriptors is u sed to select documents and snippets. The extraction and scoring of candidate answers is based on proximity measurements within the research descriptor elements and a number of secondary factors. We participated to all the subtasks and submitted 18 runs (for 16 sub-tasks). The evaluation results for manual transcripts range from 31% to 45% for accuracy depending on the task and from 16 to 41% for automatic transcripts.

8th International Conference on Natural Language Computing (NATL 2022) will
provide an excellent international forum for sharing knowledge and results in theory,
methodology and applications of Natural Language Computing. The Conference looks for
significant contributions to all major fields of the Natural Language Computing in theoretical
and practical aspects.
Authors are solicited to contribute to the conference by submitting articles that illustrate
research results, projects, surveying works and industrial experiences that describe significant
advances in the following areas, but are not limited to.

Natural Language Processing is a programmed approach to analyze text that is based on both a set of theories and a set of technologies. This forum aims to bring together researchers who have designed and build software that will analyze, understand, and generate languages that humans use naturally to address computers.

Scope
3rd International Conference on Machine Learning Techniques and NLP (MLNLP 2022) will provide an excellent international forum for sharing knowledge and results in theory, methodology and applications of Machine Learning Techniques and NLP.