We are announcing our shared task on narrative similarity and narrative representations. SemEval 2026 Task 4: https://t.co/jYfydWXv2C. We invite you to benchmark LLMs, embedding models, or even test your favorite narrative formalism. Development data is now available!

Search/acc⏩Probably the hottest BoF at #EMNLP2024! Nearly 100 researchers packed the room for 12 back-to-back talks on search foundation models - covering everything from code embeddings, distilled rerankers, ColPali, ColBERT, late chunking & smaller LMs. Killer lineup featuring

Let’s discuss: - How could story embeddings be useful in your work? - Why don’t our embeddings work well for retellings? - How can story embeddings be improved upon? More details in the paper! Paper: https://t.co/pg5jP9Ihfi Github: https://t.co/TJmrpAktc1 🧵 (6/6)

Our paper has plenty of experiments on measuring embedding capabilities for retrieval and exploring which aspects of story summaries our embeddings focus on. Big surprise: the embeddings perform well on ROCStories, a commonsense reasoning task. 🧵 (5/6)

We perform contrastive learning on summary pairs. One major twist: we pseudonymize entity mentions so the model won’t just focus on names. This augmented data strategy vastly improves performance on various narrative retrieval tasks. 🧵 (4/6)

For Tell Me Again, a dataset of multiple summaries of the same story, we collect story summaries from Wikipedia. To find reformulations of the same story, we collect summaries across Wikipedia language versions. 🧵 (3/6)

We set out to find embeddings that represent story structures. Think narrative schemas but as embeddings and without training on explicit schemas. As training data, we instead use our dataset “Tell Me Again” published earlier this year. 🧵 (2/6)

Excited to tell you all about our EMNLP paper on story embeddings! We present a novel approach for representing story summaries as embeddings. This is my first proper paper thread, so please be kind 😅 See you in Miami! 😎 🧵 (1/6)

What should the ACL peer review process be like in the future? Please cast your views in this survey: https://t.co/fBGWIwXRCo by 4th Nov 2024 #NLProc @ReviewAcl

"Tell me again! A Large-Scale Dataset of Multiple Summaries for the Same Story" a dataset of 96k summaries across 29l stories, harvested from five language versions of Wikipedia, and annotated with metadata from Wikidata. (Hatzel and Blemann, 2024) https://t.co/nreZw3Mc33

It’s cool how all of YouTube is funded by lying about the security of public WiFi

Wie wurde der vierte Tag der @DHdKonferenz grad so schön eingeläutet? CLS I und II = „die wichtigsten Sessions der Konferenz“ 🙌🏻 ich kann nicht widersprechen! Lauter spannende Vorträge von @HansHatzel @EvelynGius @BenKrautter @fotisja @janinajacke und vielen mehr #CLS #DHd

As Gregor Samsa awoke one morning from uneasy dreams, he found himself rewritten in Rust for performance reasons

posting it here to curse your timeline

https://t.co/rwrpYzL5dM

So I've made a library - "torchtyping" - for annotating a PyTorch Tensor's shape (dtype, names, layout, ...) And at runtime it checks that the annotations are consistent and correct! https://t.co/Wz29cSHCxQ Bye-bye bugs! Say hello to enforced, clear documentation of your code.