United States

The dominating paradigm for content scoring is to learn an instance-based model, i.e. to use lexical features derived from the learner answers themselves. An alternative approach that receives much less attention is however to learn a similarity-based model. We introduce an architecture that efficiently learns a similarity model and find that results on the standard ASAP dataset are on par with a BERT-based classification approach.

NAACL 2022

Similarity-Based Content Scoring – How to Make S-BERT Keep Up With BERT

s-bert

content scoring

similarity

short answer scoring

## Welcome to NAACL 2022!
The Annual Meeting of the North American Chapter of the Association for Computational Linguistics (NAACL) is taking place July 10-15, 2022 as a hybrid event, in Seattle, WA and online. We are happy to welcome all of you to conference! 
 
The main conference program features oral presentations, in-person and virtual posters and demo sessions, a plenary session for our best paper presentations and awards, keynote presentations, a plenary panel on the place of linguistics and symbolic structures in NLP, and an Industrial Track panel on Careers in NLP.
 
Posters (including Findings of NAACL 2022) and demos are grouped by areas for both the in-person and the virtual sessions. For the virtual component, the talks will be on Zoom and the posters and the demos will be in GatherTown. The Student Research Workshop and will have an oral session and a poster session.
 
The program also features 6 Tutorials and 26 Workshops.
 
 We wish you a wonderful conference!
 
[The NAACL 2022 Organizing Committee](https://2022.naacl.org/committees/organization/)

2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics

workshop paper

In this paper, we explore the role of topic information in student essays from an argument mining perspective. We cluster a recently released corpus through topic modeling into prompts and train argument identification models on various data settings. Results show that, given the same amount of training data, prompt-specific training performs better than cross-prompt training. However, the advantage can be overcome by introducing large amounts of cross-prompt training data.

Don’t Drop the Topic – The Role of the Prompt in Argument Identification in Student Writing

When listening comprehension is tested as a free-text production task, a challenge for scoring the answers is the resulting wide range of spelling variants. When judging whether a variant is acceptable or not, human raters perform a complex holistic decision. In this paper, we present a corpus study in which we analyze human acceptability decisions in a high stakes test for German. We show that for human experts, spelling variants are harder to score consistently than other answer variants. Furthermore, we examine how the decision can be operationalized using features that could be applied by an automatic scoring system. We show that simple measures like edit distance and phonetic similarity between a given answer and the target answer can model the human acceptability decisions with the same inter-annotator agreement as humans, and discuss implications of the remaining inconsistencies.

‘Meet Me at the Ribary’ – Acceptability of Spelling Variants in Free-Text Answers to Listening Comprehension Prompts

Automatic grouping of textual answers has the potential of allowing batch grading, but is challenging because the answers, especially longer essays, have many claims. To explore the feasibility of grouping together answers based on their semantic meaning, this paper investigates the grouping of short textual answers, proxies of single claims. This is approached as a paraphrase identification task, where neural and non-neural sentence embeddings and a paraphrase identification model are tested. These methods are evaluated on a dataset consisting of over 4000 short textual answers from various disciplines. The results map out the suitable question types for the paraphrase identification model and those for the neural and non-neural methods.

Towards Automatic Short Answer Assessment for Finnish as a Paraphrase Retrieval Task

Discovering individuals' suicidality on social media has become increasingly important. Many researchers have studied to detect suicidality by using a suicide dictionary. However, while prior work focused on matching a word in a post with a suicide dictionary without considering contexts, little attention has been paid to how the word can be associated with the suicide-related context. To address this problem, we propose a suicidality detection model based on a graph neural network to grasp the dynamic semantic information of the suicide vocabulary by learning the relations between a given post and words. The extensive evaluation demonstrates that the proposed model achieves higher performance than the state-of-the-art methods. We believe the proposed model has great utility in identifying the suicidality of individuals and hence preventing individuals from potential suicide risks at an early stage.

Detecting Suicidality with a Contextual Graph Neural Network

There is growing evidence that mobile text message exchanges between patients and therapists can augment traditional cognitive behavioral therapy. The automatic characterization of patient thinking patterns in this asynchronous text communication may guide treatment and assist in therapist training. In this work, we automatically identify distorted thinking in text-based patient-therapist exchanges, investigating the role of conversation history (context) in distortion prediction. We identify six unique types of cognitive distortions and utilize BERT-based architectures to represent text messages within the context of the conversation. We propose two approaches for leveraging dynamic conversation context in model training. By representing the text messages within the context of the broader patient-therapist conversation, the models better emulate the therapist's task of recognizing distorted thoughts. This multi-turn classification approach also leverages the clustering of distorted thinking in the conversation timeline. We demonstrate that including conversation context, including the proposed dynamic context methods, improves distortion prediction performance. The proposed architectures and conversation encoding approaches achieve performance comparable to inter-rater agreement. The presence of any distorted thinking is identified with relatively high performance at 0.73 F1, significantly outperforming the best context-agnostic models (0.68 F1).

Identifying Distorted Thinking in Patient-Therapist Text Message Exchanges by Leveraging Dynamic Multi-Turn Context

This study examined differences in linguistic features produced by autistic and neurotypical (NT) children during brief picture descriptions, and assessed feature stability over time. Weekly speech samples from well-characterized partic- ipants were collected using a telephony system designed to improve access for geographically isolated and historically marginalized commu- nities. Results showed stable group differences in certain acoustic features, some of which may potentially serve as key outcome measures in future treatment studies. These results high- light the importance of eliciting semi-structured speech samples in a variety of contexts over time, and adds to a growing body of research showing that fine-grained naturalistic commu- nication features hold promise for intervention research.

Identifying stable speech-language markers of autism in children: Preliminary evidence from a longitudinal telephony-based study

Formulation is central to clinical practice. Formulation has a factor weighing, pattern recognition and explanatory hypothesis modelling focus. Formulation attempts to make sense of why a person presents in a certain state at a certain time and context, and how that state may be best managed to enhance mental health, safety and optimal change. Inherent to the clinical need for formulation is an appreciation of the complexities, uncertainty and limits of applying theoretical concepts and symptom, diagnostic and risk categories to human experience; or attaching meaning or weight to any particular factor in an individual’s history or mental state without considering the broader biopsychosocial and cultural context. With specific reference to suicide prevention, this paper considers the need and potential for the computational linguistics community to be both cognisant of and ethically contribute to the clinical formulation process.

The ethical role of computational linguistics in digital psychological formulation and suicide prevention

Natural language processing tools have been shown to be effective for detecting symptoms of schizophrenia in transcribed speech. We analyze and assess the contribution of the various syntactic and morphological categories towards successful machine classification of texts produced by subjects with schizophrenia and by others. Specifically, we fine-tune a language model for the classification task, and mask all words that are attributed with each category of interest. The speech samples were generated in a controlled way by interviewing inpatients who were officially diagnosed with schizophrenia, and a corresponding group of healthy controls. All participants are native Hebrew speakers. Our results show that nouns are the most significant category for classification performance.

Masking Morphosyntactic Categories to Evaluate Salience for Schizophrenia Diagnosis

There are many different forms of psychotherapy. Itemized inventories of psychotherapeutic interventions provide a mechanism for evaluating the quality of care received by clients and for conducting research on how psychotherapy helps. However, evaluations such as these are slow, expensive, and are rarely used outside of well-funded research studies. Natural language processing research has progressed to allow automating such tasks. Yet, NLP work in this area has been restricted to evaluating a single approach to treatment, when prior re- search indicates therapists used a wide variety of interventions with their clients, often in the same session. In this paper, we frame this scenario as a multi-label classification task, and develop a group of models aimed at predicting a wide variety of therapist talk-turn level orientations. Our models achieve F1 macro scores of 0.5, with the class F1 ranging from 0.36 to 0.67. We present analyses which offer insights into the capability of such models to capture psychotherapy approaches, and which may complement human judgment.

Psychotherapy is Not One Thing: Simultaneous Modeling of Different Therapeutic Approaches

Evidence has demonstrated the presence of similarities in language use across people with various mental health conditions. In this work, we investigate these relationships both as described in literature and as a data analysis problem. We also introduce a novel transfer learning-based approach that learns from linguistic feature spaces of previous conditions and predicts unknown ones. Our model achieves strong performance, with F\textsubscript{1} scores of 0.75, 0.80, and 0.76 at detecting depression, stress, and suicidal ideation in a first-of-its-kind transfer task and offering promising evidence that language models can harness learned patterns from known mental health conditions to aid in their prediction of others that may lie latent.

Similarity-Based Content Scoring – How to Make S-BERT Keep Up With BERT

Downloads

Next from NAACL 2022

Don’t Drop the Topic – The Role of the Prompt in Argument Identification in Student Writing

Similar lecture

SemEval-2022 Task 8: Multi-lingual News Article Similarity

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES