the proceedings contain 21 papers. the topics discussed include: improving the generalizability of text-based emotion detection by leveraging transformers with psycholinguistic features;fine-grained extraction and cla...
ISBN:
(纸本)9781959429203
the proceedings contain 21 papers. the topics discussed include: improving the generalizability of text-based emotion detection by leveraging transformers with psycholinguistic features;fine-grained extraction and classification of skill requirements in German-speaking job ads;experiencer-specific emotion and appraisal prediction;understanding narratives from demographic survey data: a comparative study with multiple neural topic models;to prefer or to choose? generating agency and power counterfactuals jointly for gender bias mitigation;conspiracy narratives in the protest movement against COVID-19 restrictions in Germany. A long-term content analysis of telegram chat groups;conditional language models for community-level linguistic variation;examining political rhetoric with epistemic stance detection;and linguistic elements of engaging customer service discourse on social media.
the proceedings contain 15 papers. the topics discussed include: multilevel hypernode graphs for effective and efficient entity linking;cross-modal contextualized hidden state projection method for expanding of taxono...
the proceedings contain 15 papers. the topics discussed include: multilevel hypernode graphs for effective and efficient entity linking;cross-modal contextualized hidden state projection method for expanding of taxonomic graphs;sharing parameter by conjugation for knowledge graph embeddings in complex space;a clique-based graphical approach to detect interpretable adjectival senses in Hungarian;the effectiveness of masked language modeling and adapters for factual knowledge injection;text-aware graph embeddings for donation behavior prediction;word sense disambiguation of French lexicographical examples using lexical networks;temporal graph analysis of misinformation spreaders in social media;IJS at TextGraphs-16 naturallanguage premise selection task: will contextual information improve naturallanguage premise selection?;and keyword-based naturallanguage premise selection for an automatic mathematical statement proving.
the proceedings contain 21 papers. the topics discussed include: the early modern Dutch mediascape. detecting media mentions in chronicles using word embeddings and CRF;FrameNet-like annotation of olfactory informatio...
ISBN:
(纸本)9781954085916
the proceedings contain 21 papers. the topics discussed include: the early modern Dutch mediascape. detecting media mentions in chronicles using word embeddings and CRF;FrameNet-like annotation of olfactory information in texts;Batavia asked for advice. pretrained language models for named entity recognition in historical texts;quantifying contextual aspects of inter-annotator agreement in intertextuality research;the multilingual corpus of survey questionnaires query interface;the FairyNet corpus - character networks for German fairy tales;end-to-end style-conditioned poetry generation: what does it take to learn from examples alone?;emotion classification in German plays with transformer-based language models pretrained on historical and contemporary language;automating the detection of poetic features: the limerick as model organism;unsupervised adverbial identification in modern Chinese literature;and data-driven detection of general chiasmi using lexical and semantic features.
Assessing the perception of street environments and understanding the relationships between their aesthetic qualities and pedestrian experiences are critical to promoting walking behaviour and enhancing urban resident...
详细信息
ISBN:
(纸本)9789887891826
Assessing the perception of street environments and understanding the relationships between their aesthetic qualities and pedestrian experiences are critical to promoting walking behaviour and enhancing urban residents' long-term well-being. While Machine Learning-based analysis of Street View Imagery (SVI) has enabled a range of streetscape studies, the relationship between the visual qualities of cityscapes and people's emotional responses is still under studied. this study used recently developed computational methods to quantify urban street qualities and related sentiments. It collected online reviews and employed naturallanguageprocessing (NLP) methods to understand how people perceive streets and which environmental features contribute to positive and negative street perceptions. the analytical framework developed in this study can support other high-resolution studies into the spatial-temporal perception of cityscapes in high-density cities across the world.
We study the presence of heteronormative biases and prejudice against interracial romantic relationships in large language models by performing controlled name-replacement experiments for the task of relationship pred...
详细信息
ISBN:
(纸本)9798891761643
We study the presence of heteronormative biases and prejudice against interracial romantic relationships in large language models by performing controlled name-replacement experiments for the task of relationship prediction. We show that models are less likely to predict romantic relationships for (a) same-gender character pairs than different-gender pairs;and (b) intra/inter-racial character pairs involving Asian names as compared to Black, Hispanic, or White names. We examine the contextualized embeddings of first names and find that gender for Asian names is less discernible than non-Asian names. We discuss the social implications of our findings, underlining the need to prioritize the development of inclusive and equitable technology.
the proceedings contain 29 papers. the topics discussed include: BERTweet: a pre-trained language model for English tweets;NeuralQA: a usable library for question answering (contextual query expansion + BERT) on large...
ISBN:
(纸本)9781952148620
the proceedings contain 29 papers. the topics discussed include: BERTweet: a pre-trained language model for English tweets;NeuralQA: a usable library for question answering (contextual query expansion + BERT) on large datasets;Wikipedia2Vec: an efficient toolkit for learning and visualizing the embeddings of words and entities from Wikipedia;ARES: a reading comprehension ensembling service;transformers: state-of-the-art naturallanguageprocessing;AdapterHub: a framework for adapting transformers;HUMAN: hierarchical universal modular annotator;DeezyMatch: a flexible deep learning approach to fuzzy string matching;CoSaTa: a constraint satisfaction solver and interpreted language for semi-structured tables of sentences;a technical question answering system with transfer learning;and the language interpretability tool: extensible, interactive visualizations and analysis for NLP models.
Despite significant advancements in naturallanguage generation, controlling language models to produce texts with desired attributes remains a formidable challenge. In this work, we introduce RSA-Control, a training-...
详细信息
ISBN:
(纸本)9798891761643
Despite significant advancements in naturallanguage generation, controlling language models to produce texts with desired attributes remains a formidable challenge. In this work, we introduce RSA-Control, a training-free controllable text generation framework grounded in pragmatics. RSA-Control directs the generation process by recursively reasoning between imaginary speakers and listeners, enhancing the likelihood that target attributes are correctly interpreted by listeners amidst distractors. Additionally, we introduce a self-adjustable rationality parameter, which allows for automatic adjustment of control strength based on context. Our experiments, conducted with two task types and two types of language models, demonstrate that RSA-Control achieves strong attribute control while maintaining language fluency and content consistency. Our code is available at https://***/Ewanwong/RSA-Control.
In real-world scenarios, it is desirable for embodied agents to have the ability to leverage human language to gain explicit or implicit knowledge for learning tasks. Despite recent progress, most previous approaches ...
详细信息
ISBN:
(纸本)9798891761643
In real-world scenarios, it is desirable for embodied agents to have the ability to leverage human language to gain explicit or implicit knowledge for learning tasks. Despite recent progress, most previous approaches adopt simple low-level instructions as language inputs, which may not reflect natural human communication. It's not clear how to incorporate rich language use to facilitate task learning. To address this question, this paper studies different types of language inputs in facilitating reinforcement learning (RL) embodied agents. More specifically, we examine how different levels of language informativeness (i.e., feedback on past behaviors and future guidance) and diversity (i.e., variation of language expressions) impact agent learning and inference. Our empirical results based on four RL benchmarks demonstrate that agents trained with diverse and informative language feedback can achieve enhanced generalization and fast adaptation to new tasks. these findings highlight the pivotal role of language use in teaching embodied agents new tasks in an open world. (1)
Nested Named Entity Recognition (NER) poses a significant challenge in naturallanguageprocessing (NLP), demanding sophisticated techniques to identify entities within entities. this research investigates the applica...
详细信息
ISBN:
(纸本)9798891761643
Nested Named Entity Recognition (NER) poses a significant challenge in naturallanguageprocessing (NLP), demanding sophisticated techniques to identify entities within entities. this research investigates the application of Large language Models (LLMs) to nested NER, exploring methodologies from prior work and introducing specific reasoning techniques and instructions to improve LLM efficacy. through experiments conducted on the ACE 2004, ACE 2005, and GENIA datasets, we evaluate the impact of these approaches on nested NER performance. Results indicate that output format critically influences nested NER performance, methodologies from previous works are less effective, and our nested NER-tailored instructions significantly enhance performance. Additionally, we find that label information and descriptions of nested cases are crucial in eliciting the capabilities of LLMs for nested NER, especially in specific domains (i.e., the GENIA dataset). However, these methods still do not outperform BERT-based models, highlighting the ongoing need for innovative approaches in nested NER with LLMs.
Large language Models (LLMs) show remarkable performance on a wide variety of tasks. Most LLMs split text into multi-character tokens and process them as atomic units without direct access to individual characters. th...
详细信息
ISBN:
(纸本)9798891761643
Large language Models (LLMs) show remarkable performance on a wide variety of tasks. Most LLMs split text into multi-character tokens and process them as atomic units without direct access to individual characters. this raises the question: To what extent can LLMs learn orthographic information? To answer this, we propose a new benchmark, CUTE, which features a collection of tasks designed to test the orthographic knowledge of LLMs. We evaluate popular LLMs on CUTE, finding that most of them seem to know the spelling of their tokens, yet fail to use this information effectively to manipulate text, calling into question how much of this knowledge is generalizable.
暂无评论