Large language models (LLMs) are increasingly used to make sense of unstructured data, but their use in contexts like conversation analysis, where sensemaking is often human-driven, iterative, and subjective, is underexplored. We introduce Forage, a retrieval-augmented generation (RAG) tool for making sense of conversation data through exploratory search. We report on user studies with 27 participants across four user groups—including NPR journalists and municipal staff—observing how Forage is used to explore and analyze conversation data. We find Forage supports insight confirmation and generation, providing structure and novel insight about search results compared to a non-LLM-enabled search tool. Driven by the goal of generating multiple perspectives in Forage, we present Wild Forage, a design provocation that generates and presents multiple interpretations of the same data along a specified axis of potential interpretive difference, like political orientation. Expert user studies show that exposure to other interpretations through Wild Forage can help users meaningfully consider their assumptions in sensemaking, but findings also highlight the importance of future work to leverage this opportunity while avoiding potential harms, like stereotyping.

The time at which a message is communicated is a vital piece of metadata in many real-world natural language processing tasks such as Topic Detection and Tracking (TDT). TDT systems aim to cluster a corpus of news articles by event, and in that context, stories that describe the same event are likely to have been written at around the same time. Prior work on time modeling for TDT takes this into account, but does not well capture how time interacts with the semantic nature of the event. For example, stories about a tropical storm are likely to be written within a short time interval, while stories about a movie release may appear over weeks or months. In our work, we design a neural method that fuses temporal and textual information into a single representation of news documents for event detection. We fine-tune these time-aware document embeddings with a triplet loss architecture, integrate the model into downstream TDT systems, and evaluate the systems on two benchmark TDT data sets in English. In the retrospective setting, we apply clustering algorithms to the time-aware embeddings and show substantial improvements over baselines on the News2013 data set. In the online streaming setting, we add our document encoder to an existing state-of-the-art TDT pipeline and demonstrate that it can benefit the overall performance. We conduct ablation studies on the time representation and fusion algorithm strategies, showing that our proposed model outperforms alternative strategies. Finally, we probe the model to examine how it handles recurring events more effectively than previous TDT systems.

Educational data scientists often conduct research with the hopes of translating findings into lasting change through policy, civil society, or other channels. However, the bridge from research to practice can be fraught with sociopolitical frictions that impede, or altogether block, such translations-especially when they are contentious or otherwise difficult to achieve. Focusing on one entrenched educational equity issue in US public schools-racial and ethnic segregation-we conduct randomized email outreach experiments and surveys to explore how local school districts respond to algorithmically-generated school catchment areas ("attendance boundaries") designed to foster more diverse and integrated schools. Cold email outreach to approximately 4,320 elected school board members across over 800 school districts informing them of potential boundary changes reveals a large average open rate of nearly 40%, but a relatively small click-through rate of 2.5% to an interactive dashboard depicting such changes. Board members, however, appear responsive to different messaging techniques---particularly those that dovetail issues of racial and ethnic diversity with other top-of-mind issues (like school capacity planning). On the other hand, media coverage of the research drives more dashboard engagement, especially in more segregated districts. A small but rich set of survey responses from school board and community members across several districts identify data and operational bottlenecks to implementing boundary changes to foster more diverse schools, but also share affirmative comments on the potential viability of such changes. Together, our findings may support educational data scientists in more effectively disseminating research that aims to bridge educational inequalities through systems-level change.

As political attitudes have diverged ideologically in the United States, political speech has diverged lingusitically. The ever-widening polarization between the US political parties is accelerated by an erosion of mutual understanding between them. We aim to make these communities more comprehensible to each other with a framework that probes community-specific responses to the same survey questions using community language models CommunityLM. In our framework we identify committed partisan members for each community on Twitter and fine-tune LMs on the tweets authored by them. We then assess the worldviews of the two groups using prompt-based probing of their corresponding LMs, with prompts that elicit opinions about public figures and groups surveyed by the American National Election Studies (ANES) 2020 Exploratory Testing Survey. We compare the responses generated by the LMs to the ANES survey results, and find a level of alignment that greatly exceeds several baseline methods. Our work aims to show that we can use community LMs to query the worldview of any group of people given a sufficiently large sample of their social media discussions or media diet.

Social media data such as Twitter messages (“tweets”) pose a particular challenge to NLP systems because of their short, noisy, and colloquial nature. Tasks such as Named Entity Recognition (NER) and syntactic parsing require highly domain-matched training data for good performance. To date, there is no complete training corpus for both NER and syntactic analysis (e.g., part of speech tagging, dependency parsing) of tweets. While there are some publicly available annotated NLP datasets of tweets, they are only designed for individual tasks. In this study, we aim to create Tweebank-NER, an English NER corpus based on Tweebank V2 (TB2), train state-of-the-art (SOTA) Tweet NLP models on TB2, and release an NLP pipeline called Twitter-Stanza. We annotate named entities in TB2 using Amazon Mechanical Turk and measure the quality of our annotations. We train the Stanza pipeline on TB2 and compare with alternative NLP frameworks (e.g., FLAIR, spaCy) and transformer-based models. The Stanza tokenizer and lemmatizer achieve SOTA performance on TB2, while the Stanza NER tagger, part-of-speech (POS) tagger, and dependency parser achieve competitive performance against non-transformer models. The transformer-based models establish a strong baseline in Tweebank-NER and achieve the new SOTA performance in POS tagging and dependency parsing on TB2. We release the dataset and make both the Stanza pipeline and BERTweet-based models available “off-the-shelf” for use in future Tweet NLP research. Our source code, data, and pre-trained models are available at: https://github.com/social-machines/TweebankNLP.

We introduce RadioTalk, a corpus of speech recognition transcripts sampled from talk radio broadcasts in the United States between October of 2018 and March of 2019. The corpus is intended for use by researchers in the fields of natural language processing, conversational analysis, and the social sciences. The corpus encompasses approximately 2.8 billion words of automatically transcribed speech from 284,000 hours of radio, together with metadata about the speech, such as geographical location, speaker turn boundaries, gender, and radio program information. In this paper we summarize why and how we prepared the corpus, give some descriptive statistics on stations, shows and speakers, and carry out a few high-level analyses.

This paper describes unsupervised strategies for estimating relative accuracy differences between acoustic models or language models used for automatic speech recognition. To test acoustic models, the approach extends ideas used for unsupervised discriminative training to include a more explicit validation on held out data. To test language models, we use a dual interpretation of the same process, this time allowing us to measure differences by exploiting expected ‘truth gradients’ between strong and weak acoustic models. The paper shows correlations between supervised and unsupervised measures across a range of acoustic model and language model variations. We also use unsupervised tests to assess the non-stationary nature of mobile speech input. Index Terms: speech recognition, unsupervised testing, nonstationary distributions

Article Free Access Share on Agglomerative clustering of a search engine query log Authors: Doug Beeferman Lycos Inc., 400-2 Totten Pond Road, Waltham, MA Lycos Inc., 400-2 Totten Pond Road, Waltham, MAView Profile , Adam Berger School of Computer Science, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA School of Computer Science, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PAView Profile Authors Info & Claims KDD '00: Proceedings of the sixth ACM SIGKDD international conference on Knowledge discovery and data miningAugust 2000 Pages 407–416https://doi.org/10.1145/347090.347176Online:01 August 2000Publication History 499citation3,529DownloadsMetricsTotal Citations499Total Downloads3,529Last 12 Months149Last 6 weeks22 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteeReaderPDF

N-gram language models are frequently used by the speech recognition systems to constrain and guide the search. N-gram models use only the last N-1 words to predict the next word. Typical values of N that are used range from 2-4. N-gram language models thus lack the long-term context information. We show that the predictive power of the N-gram language models can be improved by using long-term context information about the topic of discussion. We use information retrieval techniques to generalize the available context information for topic-dependent language modeling. We demonstrate the effectiveness of this technique by performing experiments on the Wall Street Journal text corpus, which is a relatively difficult task for topic-dependent language modeling since the text is relatively homogeneous. The proposed method can reduce the perplexity of the baseline language model by 37%, indicating the predictive power of the topic-dependent language model.

This paper describes a lightweight method for the automatic insertion of intra-sentence punctuation into text. Despite the intuition that pauses in an acoustic stream are a positive indicator for some types of punctuation, this work will demonstrate the feasibility of a system which relies solely on lexical information. Besides its potential role in a speech recognition system, such a system could serve equally well in non-speech applications such as automatic grammar correction in a word processor and parsing of spoken text. After describing the design of a punctuation-restoration system, which relies on a trigram language model and a straightforward application of the Viterbi algorithm, we summarize results, both quantitative and subjective, of the performance and behavior of a prototype system.

This paper introduces new methods based on exponential families for modeling the correlations between words in text and speech. While previous work assumed the effects of word co-occurrence statistics to be constant over a window of several hundred words, we show that their influence is nonstationary on a much smaller time scale. Empirical data drawn from English and Japanese text, as well as conversational speech, reveals that the "attraction" between words decays exponentially, while stylistic and syntactic contraints create a "repulsion" between words that discourages close co-occurrence. We show that these characteristics are well described by simple mixture models based on two-stage exponential distributions which can be trained using the EM algorithm. The resulting distance distributions can then be incorporated as penalizing features in an exponential language model.

"Prose rhythm" is a widely observed but scarcely quantified phenomenon. We describe an information-theoretic model for measuring the regularity of lexical stress in English texts, and use it in combination with trigram language models to demonstrate a relationship between the probability of word sequences in English and the amount of rhythm present in them. We find that the stream of lexical stress in text from the Wall Street Journal has an entropy rate of less than 0.75 bits per syllable for common sentences. We observe that the average number of syllables per word is greater for rarer word sequences, and to normalize for this effect we run control experiments to show that the choice of word order contributes significantly to stress regularity, and increasingly with lexical probability.