Thailand

We present a new probing dataset named *PROST: Physical Reasoning about Objects Through Space and Time*. 
This dataset contains 18,736 multiple-choice questions made from 14 manually curated templates, covering 10 physical reasoning concepts. All questions are designed to probe both causal and masked language models in a zero-shot setting. We conduct an extensive analysis which demonstrates that state-of-the-art pretrained models are inadequate at physical reasoning: they are influenced by the order in which answer options are presented to them, they struggle when the superlative in a question is inverted (e.g., *most* &lt;-&gt; *least*), and increasing the amount of pretraining data and parameters only yields minimal improvements. These results provide support for the hypothesis that current pretrained models&#39; ability to reason about physical interactions is inherently limited by a lack of real world experience. By highlighting these limitations, we hope to motivate the development of models with a human-like understanding of the physical world.

ACL-IJCNLP 2021

{PROST}: {P}hysical Reasoning about Objects through Space and Time

grounding language

physical reasoning

probe

dataset

The 45th Annual Meeting of the Cognitive Science Society will take place in Sydney, Australia as a modified hybrid conference. Presentations from the main-session room will be live-streamed every day for all events. This will include all invited talks and award sessions. Recordings of all CogSci 2023 sessions will be made available for on-demand viewing after the conference.<br>
The in-person component will be held at the International Convention Centre Sydney at Darling Harbour. The Conference will take place Wednesday July 26th – Saturday July 29th, 2023 (Wednesday, July 26th is the Workshops Day).

Join us!

<br>[**The Program at a Glance can be found here**](https://cognitivesciencesociety.org/wp-content/uploads/2023/07/COgSci-PAAG-V2.pdf)
<br>[**The Detailed Program can be found here**](https://online.fliphtml5.com/ebtyf/mswz/)
<br><br>

#### **CogSci 2023 Program Book**
<iframe style="width:700px;height:400px" src="https://online.fliphtml5.com/ebtyf/tzgk/"  seamless="seamless" scrolling="no" frameborder="0" allowtransparency="true" allowfullscreen="true" ></iframe>
<br>

CogSci 2023

The 45th Annual Meeting of the Cognitive Science Society presents the latest research across cognitive science and highlights the theme of Cognition in Context.

We present a new probing dataset named *PROST: Physical Reasoning about Objects Through Space and Time*. 
This dataset contains 18,736 multiple-choice questions made from 14 manually curated templates, covering 10 physical reasoning concepts. All questions are designed to probe both causal and masked language models in a zero-shot setting. We conduct an extensive analysis which demonstrates that state-of-the-art pretrained models are inadequate at physical reasoning: they are influenced by the order in which answer options are presented to them, they struggle when the superlative in a question is inverted (e.g., *most* <-> *least*), and increasing the amount of pretraining data and parameters only yields minimal improvements. These results provide support for the hypothesis that current pretrained models' ability to reason about physical interactions is inherently limited by a lack of real world experience. By highlighting these limitations, we hope to motivate the development of models with a human-like understanding of the physical world.

technical paper

**Welcome to ACL-IJCNLP 2021!**

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP). 

As in previous years, the program of the conference includes a poster session, tutorials, workshops and demonstrations in addition to the main conference.


We were able to keep the registration fees similar to those charged for the virtual ACL 2020. The one fee allows attendance at the main conference and any/all tutorials and workshops. These fees would be $125 Regular Early and $175 Regular Late; $50 Student Early and $75 Student Late. Early registration closes at midnight July 11, 2021 (Eastern Daylight Time).

**Reminder:** It is ACL’s policy that at least one author of each accepted paper (including ACL Finding papers) must register for the conference.

**Reminder2:** Underline site will open closer to the event. If you already registered you will receive access detail

Registration is now open

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP).

Although automated metrics are commonly used to evaluate NLG systems, they often correlate poorly with human judgements. Newer metrics such as BERTScore have addressed many weaknesses in prior metrics such as BLEU and ROUGE, which rely on n-gram matching. These newer methods, however, are still limited in that they do not consider the generation context, so they cannot properly reward generated text that is correct but deviates from the given reference. 
In this paper, we propose Language Model Augmented Relevance Score (MARS), a new context-aware metric for NLG evaluation. MARS leverages off-the-shelf language models, guided by reinforcement learning, to create augmented references that consider both the generation context and available human references, which are then used as additional references to score generated text. Compared with seven existing metrics in three common NLG tasks, MARS not only achieves higher correlation with human reference judgements, but also differentiates well-formed candidates from adversarial samples to a larger degree.

Language Model Augmented Relevance Score

While counterfactual examples are useful for analysis and training of NLP models, current generation methods either rely on manual labor to create very few counterfactuals, or only instantiate limited types of perturbations such as paraphrases or word substitutions. We present Polyjuice, a general-purpose counterfactual generator that allows for control over perturbation types and locations, trained by finetuning GPT-2 on multiple datasets of paired sentences. We show that Polyjuice produces diverse sets of realistic counterfactuals, which in turn are useful in various distinct applications: improving training and evaluation on three different tasks (with around 70% less annotation effort than manual generation), augmenting state-of-the-art explanation techniques, and supporting systematic counterfactual error analysis by revealing behaviors easily missed by human experts.

Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models

Generating metaphors is a difficult task as it requires understanding nuanced relationships between abstract concepts. In this paper, we aim to generate a metaphoric sentence given a literal expression by replacing relevant verbs. Guided by conceptual metaphor theory, we propose to control the generation process by encoding conceptual mappings between cognitive domains to generate meaningful metaphoric expressions. To achieve this, we develop two methods: 1) using FrameNet-based embeddings to learn mappings between domains and applying them at the lexical level (CM-Lex), and 2) deriving source/target pairs to train a controlled seq-to-seq generation model (CM-BART). 
We assess our methods through automatic and human evaluation for basic metaphoricity and conceptual metaphor presence. We show that the unsupervised CM-Lex model is competitive with recent deep learning metaphor generation systems, and CM-BART outperforms all other models both in automatic and human evaluations.

Metaphor Generation with Conceptual Mappings

Identifying relations from dialogues is more challenging than traditional sentence-level relation extraction (RE), since the difficulties of speaker information representation and the long-range semantic reasoning. Despite the successful efforts, existing methods do not fully consider the particularity of dialogues, making them difficult to truly understand the semantics between conversational arguments. In this paper, we propose two beneficial tasks, speaker prediction and trigger words prediction, to enhance the extraction of dialogue-based relations. Specifically, speaker prediction captures the characteristics of speaker-related entities, and the trigger words prediction provides supportive contexts for relations between arguments. Extensive experiments on the DialogRE dataset show noticeable improvements compared to the baseline models, which achieves a new state-of-the-art performance with a 65.5% of F1 score and a 60.5% of F1c score, respectively.

Enhancing Dialogue-based Relation Extraction by Speaker and Trigger Words Prediction

Script reasoning infers subsequent events from a given event chain, which involves the ability to understand relations between events. A human-labeled script reasoning dataset is usually of small size with limited event relations, which highlights the necessity to leverage external eventuality knowledge graphs (KG) consisting of numerous triple facts to describe the inferential relation between events. Existing methods adopt a "retrieval and integration" paradigm to focus merely on the graph triples that have event overlap with a script, but ignore much more supportive triples in the KG with similar inferential patterns, leading to under-exploiting. To fully exploit the KG, we propose a knowledge model to learn the inferential relations between events from the whole eventuality KG and then support downstream models by directly capturing the relation between events in a script. We further present a neural script adapter to extend the knowledge model for inferring the associated relations between an event chain and a subsequent event candidate. We evaluate the proposed approach on a popular multi-choice narrative cloze task for script reasoning and achieve new state-of-the-art accuracy, compared with baselines either incorporating external KG or not.

Modeling Event-Pair Relations in External Knowledge Graphs for Script Reasoning

Word Embedding maps words to vectors of real numbers. It is derived from a large corpus and is known to capture semantic knowledge from the corpus. Word Embedding is a critical component of many state-of-the-art Deep Learning techniques. However, generating good Word Embeddings is a special challenge for low-resource languages such as Nepali due to the unavailability of large text corpus. In this paper, we present NPVec1 which consists of 25 state-of-art Word Embeddings for Nepali that we have derived from a large corpus using GloVe, Word2Vec, fastText, and BERT. We further provide intrinsic and extrinsic evaluations of these Embeddings using well established metrics and methods. These models are trained using 279 million word tokens and are the largest Embeddings ever trained for Nepali language. Furthermore, we have made these Embeddings publicly available to accelerate the development of Natural Language Processing (NLP) applications in Nepali.

NPVec1: Word Embeddings for Nepali - Construction and Evaluation

Static word vectors remain important in applications where word meaning has to be modelled in the absence of context. This paper attampt to learn high-quality static word vectors by utilizing contextualized language models (CLMs).

Deriving Word Vectors from Contextualized Language Models using Topic-Aware Mention Selection

We investigate how sentence-level transformers can be modified into effective sequence labelers at the token level without any direct supervision. Existing approaches to zero-shot sequence labeling do not perform well when applied on transformer-based architectures. As transformers contain multiple layers of multi-head self-attention, information in the sentence gets distributed between many tokens, negatively affecting zero-shot token-level performance. We find that a soft attention module which explicitly encourages sharpness of attention weights can significantly outperform existing methods.

Zero-shot Sequence Labeling for Transformer-based Sentence Classifiers

Deep neural networks (DNNs) have shown much empirical success in solving perceptual tasks across various cognitive modalities. While they are only loosely inspired by the biological brain, recent studies report considerable similarities between representations extracted from task-optimized DNNs and neural populations in the brain. DNNs have subsequently become a popular model class to infer computational principles underlying complex cognitive functions, and in turn, they have also emerged as a natural testbed for applying methods originally developed to probe information in neural populations. In this work, we utilize mean-field theoretic manifold analysis, a recent technique from computational neuroscience that connects geometry of feature representations with linear separability of classes, to analyze language representations from large-scale contextual embedding models. We explore representations from different model families (BERT, RoBERTa, GPT, etc.) and find evidence for emergence of linguistic manifolds across layer depth (e.g., manifolds for part-of-speech tags), especially in ambiguous data (i.e, words with multiple part-of-speech tags, or part-of-speech classes including many words). In addition, we find that the emergence of linear separability in these manifolds is driven by a combined reduction of manifolds’ radius, dimensionality and inter-manifold correlations.

Emergence of Separable Manifolds in Deep Language Representations

Transfer learning methods, and in particular domain adaptation, help exploit labeled data in one domain to improve the performance of a certain task in another domain. However, it is still not clear what factors affect the success of domain adaptation. This paper models adaptation success and selection of the most suitable source domains among several candidates in text similarity. We use descriptive domain information and cross-domain similarity metrics as predictive features. While mostly positive, the results also point to some domains where adaptation success was difficult to predict.

Downloads

Next from ACL-IJCNLP 2021

Language Model Augmented Relevance Score

Similar lecture

A Benchmark for Modeling Violation-of-Expectation in Physical Reasoning Across Event Categories

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from ACL-IJCNLP 2021

Language Model Augmented Relevance Score

Similar lecture

A Benchmark for Modeling Violation-of-Expectation in Physical Reasoning Across Event Categories

Downloads