# Stories are mixed with each other

**URL:** <https://forum.rasa.com/t/stories-are-mixed-with-each-other/32726>\
**Category:** Rasa Open Source\
**Created:** [August 18, 2020, 1:42pm UTC](https://forum.rasa.com/t/stories-are-mixed-with-each-other/32726 "2020-08-18T13:42:05Z")\
**Posts on this page:** 10\
**Page:** 1

<div class="post-metadata">

**Author:** ![sebastian](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/sebastian/32/10638_2.png) [@sebastian](https://forum.rasa.com/u/sebastian)\
**Post date:** [August 18, 2020, 1:42pm UTC](https://forum.rasa.com/t/stories-are-mixed-with-each-other/32726/1 "2020-08-18T13:42:05Z")

</div>

Hey there 🙂

in my use case there is one situation where a user walks through a three-step-dialogue and can select different paths via buttons. While the first path (first story) works perfectly, in the second path (second story) only the first and second bot action is performed correctly. The third bot action that follows an affirm-intent never is the planned one, but instead the one that follows the affirm-intent in the other story. To stick with the example: Instead of “utter\_auto\_push\_set” I always get “utter\_upsell\_info”. As mentioned before, the first story is working without any problems.

As my bot is basically an FAQ-bot, I have set the `max_history` to `1` in my `MemoizationPolicy`.

First story:

```
* no_response_to_ads
  - utter_what_type_of_ad
* ads_nondating
  - utter_no_response_to_nondating_ads
* affirm
  - utter_upsell_info

```

Second story:

```
* no_response_to_ads
  - utter_what_type_of_ad
* ads_dating
  - utter_no_response_to_dating_ads
* affirm
  - utter_auto_push_set

```

Maybe you have some advice for me, what is going on here.

Thanks in advance!

---

<div class="post-metadata">

**Author:** ![Tanja](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/tanja/32/4696_2.png) [@Tanja](https://forum.rasa.com/u/Tanja)\
**Post date:** [August 19, 2020, 6:40am UTC](https://forum.rasa.com/t/stories-are-mixed-with-each-other/32726/2 "2020-08-19T06:40:37Z")

</div>

Are you using any other policy? How does your config file look like?

Theoretically `max_history` of `1` should work. Are you sure that the intents are predicted correctly? Do you have any other story that uses the intent `affirm`?

Just to be sure, does it work if you set `max_history` to `2`?

---

<div class="post-metadata">

**Author:** ![sebastian](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/sebastian/32/10638_2.png) [@sebastian](https://forum.rasa.com/u/sebastian)\
**Post date:** [August 19, 2020, 7:43am UTC](https://forum.rasa.com/t/stories-are-mixed-with-each-other/32726/3 "2020-08-19T07:43:46Z")

</div>

Hey Tanja,

Thank you for your answer. Yes, I have a few stories with `affirm` in it. And this is what my config looks like:

```
language: de
pipeline: supervised_embeddings
policies:
  - name: MemoizationPolicy
    max_history: 1
  - name: KerasPolicy
  - name: MappingPolicy
  - name: FallbackPolicy
    nlu_threshold: 0.4
    core_threshold: 0.4
    ambiguity_threshold: 0.1
    fallback_action_name: action_default_fallback

```

For a test I have set my `MemoizationPolicy` to `2` – and it works well this way. But now most of my one-turn stories (user asks – bot acts/utters) don’t work anymore and lead to a fallback.

I was once the advice given, to use a mapping for my one-turners and try to handle the others with a higher value for the `MemoizationPolicy`. Do you think this might help to solve the problem?

**Edit** : I’ve gained some further insights that might help. I always stumble upon these problems whenever there is an intent within a multi-turn story, that is not exclusively part of that story but also appears within others (such as `affirm` or `deny`). In these cases, the bot produces either my fallback utterance or (seems to) randomly pick one of the utter-actions that immediately follows the specific intent in any of my relevant stories.

---

<div class="post-metadata">

**Author:** ![sebastian](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/sebastian/32/10638_2.png) [@sebastian](https://forum.rasa.com/u/sebastian)\
**Post date:** [August 20, 2020, 12:22pm UTC](https://forum.rasa.com/t/stories-are-mixed-with-each-other/32726/4 "2020-08-20T12:22:31Z")

</div>

Hey Tanja,

It looks like I found a solution. For all my FAQ one-turners I have mapped the intents to the corresponding actions and at the same time set the `MemoizationPolicy` back to default. This seems to work well for most of my cases until now. 🙂

---

<div class="post-metadata">

**Author:** ![sebastian](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/sebastian/32/10638_2.png) [@sebastian](https://forum.rasa.com/u/sebastian)\
**Post date:** [September 24, 2020, 12:22pm UTC](https://forum.rasa.com/t/stories-are-mixed-with-each-other/32726/5 "2020-09-24T12:22:39Z")

</div>

Hey @Tanja,

Unfortunately I need to re-open this thread as I am stumbling upon these problems again:

Whenever there is an intent in my story, that also appears in another story (usually `affirm` or `deny`), the bot “randomly” picks an action in response to this intent, that follows the `affirm`-/`deny`-intent in any of my stories. Sometimes the bot instead presents my fallback-utterance after `affirm`/`deny`. There is a striking pattern: This does **not** happen, if the story is tested right at the beginning of a new conversation. Only in case another story was initiated in this conversation beforehand, the bot fails after `affirm`/`deny` in the new story.

I have mapped most of my intents to actions, but of course `affirm`/`deny` are not mapped to a specific action. I use `MemoizationPolicy` with `max_history` of `6`:

```
language: de
pipeline: supervised_embeddings
policies:
  - name: MemoizationPolicy
    max_history: 6
  - name: KerasPolicy
  - name: MappingPolicy
  - name: FallbackPolicy
    nlu_threshold: 0.4
    core_threshold: 0.4
    ambiguity_threshold: 0.1
    fallback_action_name: action_default_fallback

```

Maybe you have an idea how I can solve this problem. 🙂

Thank you in advance!

Sebastian

---

<div class="post-metadata">

**Author:** ![sebastian](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/sebastian/32/10638_2.png) [@sebastian](https://forum.rasa.com/u/sebastian)\
**Post date:** [September 25, 2020, 8:30am UTC](https://forum.rasa.com/t/stories-are-mixed-with-each-other/32726/6 "2020-09-25T08:30:11Z")

</div>

I might have found a solution. By setting the `max_history` to `2`, everything seems to work now. I am still a little confused about `max_history` in general and I’m not sure if understand the docs correctly.

Let’s say I have the a story with three intent-actions-pairs like this:

```
## example story

* greet
- utter_greet_back
* ask_for_help
- utter_offer_help
* thank
- utter_you_are_welcome

```

Let’s imagine, the bot has presented `utter_offer_help` and the user has just typed in “Thank you”. The bot now tries to interpret that input to select the next (re-)action. Let’s say it has a high confidence to interpret “Thank You” as the intent `thank`. As far as I understood, with a max\_history of `2` the bot would now also take the the last two “steps” of the actual dialogue and check if it finds a resemblance of these two steps (+ the just interpreted intent `thank`) in any story. The two steps in this case would be the action `utter_offer_help` and the foregoing intent `ask_for_help`. If it does not find a resemblance of all three steps in this exact combination, it will `utter_default`, if it finds one, it will execute the action that corresponds to the detected story. Is this so far correct?

I am still a little confused and try to understand, why `max_history` of `6` led to failure in my case, while `max_history` of `2` now seems to work.

Thanks in advance!

---

<div class="post-metadata">

**Author:** ![Tanja](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/tanja/32/4696_2.png) [@Tanja](https://forum.rasa.com/u/Tanja)\
**Post date:** [September 28, 2020, 3:09pm UTC](https://forum.rasa.com/t/stories-are-mixed-with-each-other/32726/7 "2020-09-28T15:09:06Z")

</div>

Your explanation sounds right. If `max_history` of `6` did not work, it was most likely the case that your story did not fully match any story in the training data as all 6 previous actions need to match. Can you verify that?

---

<div class="post-metadata">

**Author:** ![sebastian](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/sebastian/32/10638_2.png) [@sebastian](https://forum.rasa.com/u/sebastian)\
**Post date:** [September 30, 2020, 3:02pm UTC](https://forum.rasa.com/t/stories-are-mixed-with-each-other/32726/8 "2020-09-30T15:02:15Z")

</div>

Hey Tanja,

yes – until now, everything seems to work fine and I can verify it. 🙂

I have one last question regarding your statement that “all 6 previous actions need to match”: What exactly is meant by `action` here? Does the `max_history` only concern the previous bot-actions or is it also sensitive to the intents that were part of the last – let’s call it – events of the conversation?

Have a nice day!

---

<div class="post-metadata">

**Author:** ![Tanja](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/tanja/32/4696_2.png) [@Tanja](https://forum.rasa.com/u/Tanja)\
**Post date:** [October 5, 2020, 1:26pm UTC](https://forum.rasa.com/t/stories-are-mixed-with-each-other/32726/9 "2020-10-05T13:26:14Z")

</div>

Sorry for the late reply. With `action` I was referring to all kind of events that happened before, so bot utterances/actions and user utterances.

---

<div class="post-metadata">

**Author:** ![sebastian](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/sebastian/32/10638_2.png) [@sebastian](https://forum.rasa.com/u/sebastian)\
**Post date:** [October 8, 2020, 12:10pm UTC](https://forum.rasa.com/t/stories-are-mixed-with-each-other/32726/10 "2020-10-08T12:10:12Z")

</div>

Thank you. 🙂