With the number of documents describing real-world events and event-oriented information needs rapidly growing on a daily basis, the need for efficient retrieval and concise presentation of ...event-related information is becoming apparent. Nonetheless, the majority of information retrieval and text summarization methods rely on shallow document representations that do not account for the semantics of events. In this article, we present event graphs, a novel event-based document representation model that filters and structures the information about events described in text. To construct the event graphs, we combine machine learning and rule-based models to extract sentence-level event mentions and determine the temporal relations between them. Building on event graphs, we present novel models for information retrieval and multi-document summarization. The information retrieval model measures the similarity between queries and documents by computing graph kernels over event graphs. The extractive multi-document summarization model selects sentences based on the relevance of the individual event mentions and the temporal structure of events. Experimental evaluation shows that our retrieval model significantly outperforms well-established retrieval models on event-oriented test collections, while the summarization model outperforms competitive models from shared multi-document summarization tasks.
Pretrained multilingual text encoders based on neural
transformer architectures
, such as multilingual BERT (mBERT) and XLM, have recently become a default paradigm for cross-lingual transfer of ...natural language processing models, rendering cross-lingual word embedding spaces (CLWEs) effectively obsolete. In this work we present a systematic empirical study focused on the suitability of the state-of-the-art multilingual encoders for cross-lingual document and sentence retrieval tasks across a number of diverse language pairs. We first treat these models as multilingual text encoders and benchmark their performance in unsupervised ad-hoc sentence- and document-level CLIR. In contrast to supervised language understanding, our results indicate that for unsupervised document-level CLIR—a setup with no relevance judgments for IR-specific fine-tuning—pretrained multilingual encoders on average fail to significantly outperform earlier models based on CLWEs. For sentence-level retrieval, we do obtain state-of-the-art performance: the peak scores, however, are met by multilingual encoders that have been further specialized, in a supervised fashion, for sentence understanding tasks, rather than using their vanilla ‘off-the-shelf’ variants. Following these results, we introduce localized relevance matching for document-level CLIR, where we independently score a query against document sections. In the second part, we evaluate multilingual encoders fine-tuned in a supervised fashion (i.e., we
learn to rank
) on English relevance data in a series of zero-shot language and domain transfer CLIR experiments. Our results show that, despite the supervision, and due to the domain and language shift, supervised re-ranking rarely improves the performance of multilingual transformers as unsupervised base rankers. Finally, only with in-domain contrastive fine-tuning (i.e., same domain, only language transfer), we manage to improve the ranking quality. We uncover substantial empirical differences between cross-lingual retrieval results and results of (zero-shot) cross-lingual transfer for monolingual retrieval in target languages, which point to “monolingual overfitting” of retrieval models trained on monolingual (English) data, even if they are based on multilingual transformers.
Recognizing semantically similar sentences or paragraphs across languages is beneficial for many tasks, ranging from cross-lingual information retrieval and plagiarism detection to machine ...translation. Recently proposed methods for predicting cross-lingual semantic similarity of short texts, however, make use of tools and resources (e.g., machine translation systems, syntactic parsers or named entity recognition) that for many languages (or language pairs) do not exist. In contrast, we propose an unsupervised and a very resource-light approach for measuring semantic similarity between texts in different languages. To operate in the bilingual (or multilingual) space, we project continuous word vectors (i.e., word embeddings) from one language to the vector space of the other language via the linear translation model. We then align words according to the similarity of their vectors in the bilingual embedding space and investigate different unsupervised measures of semantic similarity exploiting bilingual embeddings and word alignments. Requiring only a limited-size set of word translation pairs between the languages, the proposed approach is applicable to virtually any pair of languages for which there exists a sufficiently large corpus, required to learn monolingual word embeddings. Experimental results on three different datasets for measuring semantic textual similarity show that our simple resource-light approach reaches performance close to that of supervised and resource-intensive methods, displaying stability across different language pairs. Furthermore, we evaluate the proposed method on two extrinsic tasks, namely extraction of parallel sentences from comparable corpora and cross-lingual plagiarism detection, and show that it yields performance comparable to those of complex resource-intensive state-of-the-art models for the respective tasks.
In task-oriented dialogue (ToD), a user holds a conversation with an artificial agent with the aim of completing a concrete task. Although this technology represents one of the central objectives ...of AI and has been the focus of ever more intense research and development efforts, it is currently limited to a few narrow domains (e.g., food ordering, ticket booking) and a handful of languages (e.g., English, Chinese). This work provides an extensive overview of existing methods and resources in multilingual ToD as an entry point to this exciting and emerging field. We find that the most critical factor preventing the creation of truly multilingual ToD systems is the lack of datasets in most languages for both training and evaluation. In fact, acquiring annotations or human feedback for each component of modular systems or for data-hungry end-to-end systems is expensive and tedious. Hence, state-of-the-art approaches to multilingual ToD mostly rely on (zero- or few-shot) cross-lingual transfer from resource-rich languages (almost exclusively English), either by means of (i) machine translation or (ii) multilingual representations. These approaches are currently viable only for typologically similar languages and languages with parallel / monolingual corpora available. On the other hand, their effectiveness beyond these boundaries is doubtful or hard to assess due to the lack of linguistically diverse benchmarks (especially for natural language generation and end-to-end evaluation). To overcome this limitation, we draw parallels between components of the ToD pipeline and other NLP tasks, which can inspire solutions for learning in low-resource scenarios. Finally, we list additional challenges that multilinguality poses for related areas (such as speech, fluency in generated text, and human-centred evaluation), and indicate future directions that hold promise to further expand language coverage and dialogue capabilities of current ToD systems.
•Event-based automatic text simplification system.•Lexical and syntactic text simplification with content reduction.•No need for parallel datasets nor large set of handcrafted simplification ...rules.•Proposed simplification system is highly competitive.•Novel evaluation method based on measuring the postediting effort.
Automated Text Simplification (ATS) aims to transform complex texts into their simpler variants which are easier to understand to wider audiences and easier to process with natural language processing (NLP) tools. While simplification can be applied on lexical, syntactic, and discourse level, all previously proposed ATS systems only operated on the first two levels, thus failing at simplifying texts on the discourse level. We present a semantically-motivated ATS system which is the first system that is applied on the discourse level. By exploiting the state-of-the-art event extraction system, it is the first ATS system able to eliminate large portions of irrelevant information from texts, by maintaining only those parts of the original text that belong to factual event mentions. A few handcrafted rules ensure that the output of the system is syntactically simple, by placing each factual event mention in a separate short sentence, while the state-of-the-art unsupervised lexical simplification module, based on using word embeddings, replaces complex and infrequent words with their simpler variants. We perform a thorough evaluation, both automatic and manual, showing that our system produces more readable and simpler texts than the state-of-the-art ATS systems. Our newly proposed post-editing evaluation further reveals that our system requires less human effort for correcting grammaticality and meaning preservation on news articles than the state-of-the-art ATS system.
Despite extensive research efforts in recent years, computational argumentation (CA) remains one of the most challenging areas of natural language processing. The reason for this is the inherent ...complexity of the cognitive processes behind human argumentation, which integrate a plethora of different types of knowledge, ranging from topic-specific facts and common sense to rhetorical knowledge. The integration of knowledge from such a wide range in CA requires modeling capabilities far beyond many other natural language understanding tasks. Existing research on mining, assessing, reasoning over, and generating arguments largely acknowledges that much more knowledge is needed to accurately model argumentation computationally. However, a systematic overview of the types of knowledge introduced in existing CA models is missing, hindering targeted progress in the field. Adopting the operational definition of knowledge as any task-relevant normative information not provided as input, the survey paper at hand fills this gap by (1) proposing a taxonomy of types of knowledge required in CA tasks, (2) systematizing the large body of CA work according to the reliance on and exploitation of these knowledge types for the four main research areas in CA, and (3) outlining and discussing directions for future research efforts in CA.
Events play an important role in natural language processing and information retrieval due to numerous event-oriented texts and information needs. Many natural language processing and information ...retrieval applications could benefit from a structured event-oriented document representation. In this paper, we propose event graphs as a novel way of structuring event-based information from text. Nodes in event graphs represent the individual mentions of events, whereas edges represent the temporal and coreference relations between mentions. Contrary to previous natural language processing research, which has mainly focused on individual event extraction tasks, we describe a complete end-to-end system for event graph extraction from text. Our system is a three-stage pipeline that performs anchor extraction, argument extraction, and relation extraction (temporal relation extraction and event coreference resolution), each at a performance level comparable with the state of the art. We present EvExtra, a large newspaper corpus annotated with event mentions and event graphs, on which we train and evaluate our models. To measure the overall quality of the constructed event graphs, we propose two metrics based on the tensor product between automatically and manually constructed graphs. Finally, we evaluate the overall quality of event graphs with the proposed evaluation metrics and perform a headroom analysis of the system.
Geographic Adaptation of Pretrained Language Models Hofmann, Valentin; Glavaš, Goran; Ljubešić, Nikola ...
Transactions of the Association for Computational Linguistics,
04/2024, Letnik:
12
Journal Article
Recenzirano
Odprti dostop
While pretrained language models (PLMs) have been shown to possess a plethora of linguistic knowledge, the existing body of research has largely neglected extralinguistic knowledge, which is ...generally difficult to obtain by pretraining on text alone. Here, we contribute to closing this gap by examining
knowledge, i.e., knowledge about geographic variation in language. We introduce
, an intermediate training step that couples language modeling with geolocation prediction in a multi-task learning setup. We geoadapt four PLMs, covering language groups from three geographic areas, and evaluate them on five different tasks: fine-tuned (i.e., supervised) geolocation prediction, zero-shot (i.e., unsupervised) geolocation prediction, fine-tuned language identification, zero-shot language identification, and zero-shot prediction of dialect features. Geoadaptation is very successful at injecting geolinguistic knowledge into the PLMs: The geoadapted PLMs consistently outperform PLMs adapted using only language modeling (by especially wide margins on zero-shot prediction tasks), and we obtain new state-of-the-art results on two benchmarks for geolocation prediction and language identification. Furthermore, we show that the effectiveness of geoadaptation stems from its ability to
the representation space of the PLMs.
Narrative texts in electronic health records can be efficiently utilized for building decision support systems in the clinic, only if they are correctly interpreted automatically in accordance with a ...specified standard. This paper tackles the problem of developing an automated method of labeling free-form radiology reports, as a precursor for building query-capable report databases in hospitals. The analyzed dataset consists of 1295 radiology reports concerning the condition of a knee, retrospectively gathered at the Clinical Hospital Centre Rijeka, Croatia. Reports were manually labeled with one or more labels from a set of 10 most commonly occurring clinical conditions. After primary preprocessing of the texts, two sets of text classification methods were compared: (1) traditional classification models-Naive Bayes (NB), Logistic Regression (LR), Support Vector Machine (SVM), and Random Forests (RF)-coupled with Bag-of-Words (BoW) features (i.e., symbolic text representation) and (2) Convolutional Neural Network (CNN) coupled with dense word vectors (i.e., word embeddings as a semantic text representation) as input features. We resorted to nested 10-fold cross-validation to evaluate the performance of competing methods using accuracy, precision, recall, and F 1 score. The CNN with semantic word representations as input yielded the overall best performance, having a micro-averaged F 1 score of 86 . 7 % . The CNN classifier yielded particularly encouraging results for the most represented conditions: degenerative disease ( 95 . 9 % ), arthrosis ( 93 . 3 % ), and injury ( 89 . 2 % ). As a data-hungry deep learning model, the CNN, however, performed notably worse than the competing models on underrepresented classes with fewer training instances such as multicausal disease or metabolic disease. LR, RF, and SVM performed comparably well, with the obtained micro-averaged F 1 scores of 84 . 6 % , 82 . 2 % , and 82 . 1 % , respectively.