Levin et al. (2019) show experimentally that the interpretations of novel English noun compounds (e.g., stew skillet), while not fully compositional, are highly predictable based on whether the modifier and head refer to artifacts or natural kinds. Is the large language model GPT-3 governed by the same interpretive principles? To address this question, we first compare Levin et al.’s experimental data with GPT-3 generations, finding a high degree of similarity. However, this evidence is consistent with GPT-3 reasoning only about specific lexical items rather than the more abstract conceptual categories of Levin et al.’s theory. To probe more deeply, we construct prompts that require the relevant kind of conceptual reasoning. Here, we fail to find convincing evidence that GPT-3 is reasoning about more than just individual lexical items. These results highlight the importance of controlling for low-level distributional regularities when assessing whether a large language model latently encodes a deeper theory.

Transformer-based language model approaches to automated story generation currently provide state-of-the-art results. However, they still suffer from plot incoherence when generatingnarratives over time, and critically lack basiccommonsense reasoning. Furthermore, existing methods generally focus only on single-character stories, or fail to track charactersat all. To improve the coherence of generated narratives and to expand the scope ofcharacter-centric narrative generation, we introduce Commonsense-inference Augmentedneural StoryTelling (CAST), a framework forintroducing commonsense reasoning into thegeneration process with the option to model theinteraction between multiple characters. Wefind that our CAST method produces significantly more coherent, on-topic, enjoyable andfluent stories than existing models in both thesingle-character and two-character settings inthree storytelling domains.

While large pre-trained language models are powerful, their predictions often lack logical consistency across test inputs. For example, a state-of-the-art Macaw question-answering (QA) model answers <i>Yes</i> to <i>Is a sparrow a bird?</i> and <i>Does a bird have feet?</i> but answers <i>No</i> to <i>Does a sparrow have feet?</i>. To address this failure mode, we propose a framework, Consistency Correction through Relation Detection, or <b>ConCoRD</b>, for boosting the consistency and accuracy of pre-trained NLP models using pre-trained natural language inference (NLI) models without fine-tuning or re-training. Given a batch of test inputs, ConCoRD samples several candidate outputs for each input and instantiates a factor graph that accounts for both the model’s belief about the likelihood of each answer choice in isolation and the NLI model’s beliefs about pair-wise answer choice compatibility. We show that a weighted MaxSAT solver can efficiently compute high-quality answer choices under this factor graph, improving over the raw model’s predictions. Our experiments demonstrate that ConCoRD consistently boosts accuracy and consistency of off-the-shelf closed-book QA and VQA models using off-the-shelf NLI models, notably increasing accuracy of LXMERT on ConVQA by 5% absolute. See the project website (https://ericmitchell.ai/emnlp-2022-concord/) for code and data.

Current spoken dialogue systems initiate their turns after a long period of silence (700-1000ms), which leads to little real-time feedback, sluggish responses, and an overall stilted conversational flow. Humans typically respond within 200ms and successfully predicting initiation points in advance would allow spoken dialogue agents to do the same. In this work, we predict the lead-time to initiation using prosodic features from a pre-trained speech representation model (wav2vec 1.0) operating on user audio and word features from a pre-trained language model (GPT-2) operating on incremental transcriptions. To evaluate errors, we propose two metrics w.r.t. predicted and true lead times. We train and evaluate the models on the Switchboard Corpus and find that our method outperforms features from prior work on both metrics and vastly outperforms the common approach of waiting for 700ms of silence.

Automated storytelling has long captured the attention of researchers for the ubiquity of narratives in everyday life. The best human-crafted stories exhibit coherent plot, strong characters, and adherence to genres, attributes that current states-of-the-art still struggle to produce, even using transformer architectures. In this paper, we analyze works in story generation that utilize machine learning approaches to (1) address story generation controllability, (2) incorporate commonsense knowledge, (3) infer reasonable character actions, and (4) generate creative language.

Large-scale, transformer-based language models such as GPT-2 are pretrained on diverse corpora scraped from the internet. Consequently, they are prone to generating non-normative text (i.e. in violation of social norms). We introduce a technique for fine-tuning GPT-2, using a policy gradient reinforcement learning technique and a normative text classifier to produce reward and punishment values. We evaluate our technique on five data sets using automated and human participant experiments. The normative text classifier is 81-90% accurate when compared to gold-standard human judgements of normative and non-normative generated text. Our normative fine-tuning technique is able to reduce non-normative text by 27-61%, depending on the data set.